CN114283287A - Robust field adaptive image learning method based on self-training noise label correction - Google Patents

Robust field adaptive image learning method based on self-training noise label correction Download PDF

Info

Publication number
CN114283287A
CN114283287A CN202210221128.5A CN202210221128A CN114283287A CN 114283287 A CN114283287 A CN 114283287A CN 202210221128 A CN202210221128 A CN 202210221128A CN 114283287 A CN114283287 A CN 114283287A
Authority
CN
China
Prior art keywords
source domain
domain
pseudo
samples
prediction
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202210221128.5A
Other languages
Chinese (zh)
Other versions
CN114283287B (en
Inventor
李绍园
曹正涛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University of Aeronautics and Astronautics
Original Assignee
Nanjing University of Aeronautics and Astronautics
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing University of Aeronautics and Astronautics filed Critical Nanjing University of Aeronautics and Astronautics
Priority to CN202210221128.5A priority Critical patent/CN114283287B/en
Publication of CN114283287A publication Critical patent/CN114283287A/en
Application granted granted Critical
Publication of CN114283287B publication Critical patent/CN114283287B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Image Analysis (AREA)

Abstract

The invention discloses a robust field self-adaptive image learning method based on self-training noise label correction, which comprises the following steps: acquiring a source domain, a target domain image set and a source domain low-quality label; initializing various parameters; building a model and a loss function; sequentially inputting the image sets of the source domain and the target domain into two mark classifiers; the two mark classifiers detect noise for the opposite side before each iterative training, then predict pseudo marks again for the noise source domain sample and the target domain sample, and perform rebalance sampling to participate in the next iterative training; inputting a target domain pseudo label set into target domain specific network training; and after the training is finished, performing a class prediction task on the target domain image by using the target domain specific classifier. Aiming at the problem that the category distribution of a source domain is inconsistent with that of a target domain, the method adopts a rebalanced sampling pseudo-mark sample mechanism to ensure that the sampling proportion of each category of the source domain and the target domain is consistent, and the accuracy of a deep learning model on the target domain is improved.

Description

Robust field adaptive image learning method based on self-training noise label correction
Technical Field
The invention relates to a robust field self-adaptive image learning method based on self-training noise label correction.
Background
The traditional supervised learning needs a large amount of images and accurate labeling information, however, in practical situations, the collection of a large amount of accurate labels requires extremely high cost, so that the labels contain a large amount of noise. The unsupervised field self-adaptation is applied to another data set with different but similar data distribution by utilizing a training model on the data set with the accurate label in a migration mode, wherein the data set with the accurate label is a source field, and the data set without the label is a target field. Although conventional domain adaptation solves the problem of lack of supervisory information on the target domain, it ignores the problem of significant cost for source domain marker acquisition, and therefore their performance is severely degraded when there is noise in the labeled information in the source domain.
Disclosure of Invention
The invention provides a robust field adaptive image learning method based on self-training noise label correction, and aims to further improve the accuracy of the field adaptive image learning method on a target field when the problems of labeled noise and inconsistent source field and target field category distribution (category distribution offset) are faced.
In order to achieve the purpose, the invention adopts the following technical scheme:
a robust field self-adaptive image learning method based on self-training noise label correction comprises the following steps:
step 1, obtaining a source domain original data set
Figure 493234DEST_PATH_IMAGE001
And a target domain data set
Figure 354355DEST_PATH_IMAGE002
；
Wherein the content of the first and second substances,D s representing source domain raw images acquired by a network platformx si And its corresponding source domain low quality mark
Figure 637569DEST_PATH_IMAGE003
Composed source domain primitive numbersAccording to the data set, the data of the data set,N s representing a source domain raw data setD s Total number of medium samples;
D t representing the original image only by the target domainx ti The composed target domain data set is composed of,N t to representD t The number of medium target domain samples;
step 2, initializing various parameters including iteration timest=0, the secondtRound false mark thresholdγ tPre-training parametersN warm ；
And 3, building a deep learning model and a loss function, comprising the following steps: feature extractorGTwo tag classifierC 1、C 2Target domain specific classifierC t Cross entropy loss functionL ce And a consistency loss functionL sp ；
Step 4, the original data set of the source domainD s Source domain original image inx si Input feature extractorGTo extract features in an imagef si =G(x si ) Then extracting the source domain featuresf si And low quality marks corresponding to the original image of the source domain
Figure 460031DEST_PATH_IMAGE004
Is sent into two mark classifiersC 1、C 2In the middle ofWarm upTraining, trainingN warm A wheel;
step 5. in the detection stage, two mark classifiers are usedC 1、C 2Sequentially and respectively detecting the marking noise in the source domain, and mutually taking the original data sets of the source domain as the opposite sideD s Partitioning into clean source domain samples
Figure 461485DEST_PATH_IMAGE005
And noise source domain samples
Figure 394806DEST_PATH_IMAGE006
；
Step 6, two mark classifiers are usedC 1、C 2In turn, are noise source domain samples
Figure 266947DEST_PATH_IMAGE007
And a target domain data setD t Performing class prediction on each sample, and taking the prediction class as
Figure 260311DEST_PATH_IMAGE007
AndD t a pseudo-label for each sample in the set;
according toγ tFor the noise source field sample in step 6
Figure 749061DEST_PATH_IMAGE007
And a target domain data setD t In each pseudo-labeled sample, the sample sampling ratio of each category isγ t / KTo obtain a pseudo label setD sp ={
Figure 220494DEST_PATH_IMAGE008
，
Figure 212721DEST_PATH_IMAGE009
}；
Wherein the content of the first and second substances,Kthe number of categories is indicated and the number of categories,
Figure 376986DEST_PATH_IMAGE010
a set of pseudo-annotations of the source domain is represented,
Figure 821874DEST_PATH_IMAGE011
representing a target domain pseudo label set;
and 7, if the training is the first round of iterative training, then
Figure 96997DEST_PATH_IMAGE009
=
Figure 474889DEST_PATH_IMAGE008
(ii) a If not, then,
Figure 544476DEST_PATH_IMAGE009
=
Figure 7819DEST_PATH_IMAGE009
；
step 8, in the training stage, clean source domain samples are sampled
Figure 821054DEST_PATH_IMAGE005
And pseudo label setD sp Image input feature extractorGExtracting features, and inputting the extracted features and corresponding labels into two label classifiersC 1、C 2Carrying out supervision training in sequence;
for clean source domain samples
Figure 787873DEST_PATH_IMAGE005
Optimizing cross entropy loss functionL ce For pseudo label setsD sp Optimizing consistency loss functionsL sp To update the feature extractorGAnd two tag classifiersC 1、C 2；
Step 9, pseudo labeling set of target domain
Figure 28361DEST_PATH_IMAGE012
Image input feature extractorGExtracting features, and inputting the extracted features and corresponding pseudo labels into a target domain specific classification networkC t Optimizing cross entropy loss functionL ce To updateG、C t ；
Step 10, judging the current iteration timestWhether or not the maximum number of iterations has been reachedT；
If the current number of iterationstNot reaching the maximum number of iterationsTThen, the self-training is continued by returning to the step 5,t=t+1, and updateγ t=γ 0+0.05*t(ii) a Wherein the content of the first and second substances,γ 0a pseudo-mark threshold representing initialization; otherwise, go to step 11;
step 11, after the model training is finished, executing a classification prediction task, firstly using a feature extractorGExtracting features from the target domain image and inputting the extracted featuresC t And (5) performing category prediction.
The invention has the following advantages:
as mentioned above, the invention relates to a robust domain adaptive image learning method based on self-training noise label correction, which is a robust domain adaptive method based on self-training noise detection and label rebalance definition, and performs alternate training by designing a label network and a target domain specific network, wherein the label network can effectively filter label noise in a source domain through the label network, and performs rebalance sampling on pseudo label samples to solve the problem of class distribution shift (label distribution shift), and the target domain pseudo label samples are utilized to train the target domain specific network, thereby obtaining the classification capability on a target domain to realize knowledge transfer from the source domain to the target domain, and meanwhile, the invention utilizes rebalance pseudo label sampling to solve the problem of inconsistent class distribution of the source domain and the target domain, further improving under the noise condition, robustness of domain adaptive methods.
Drawings
FIG. 1 is a flow chart of a robust domain adaptive image learning method based on self-training noise label correction in an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of an integral model in an embodiment of the invention;
FIG. 3 is a flow chart illustrating the filtering of source domain marker noise according to an embodiment of the present invention;
FIG. 4 is a flow chart illustrating the generation and rebalancing of sampling pseudo labels according to an embodiment of the present invention.
Detailed Description
The noun explains:
weak enhancement means that a picture is simply turned over and translated; the strong enhancement means that two kinds of strong transformation (translation, clipping, rotation, turning, image compression and the like) and disturbance (overexposure, contrast enhancement, sharpening, black and white processing, tone separation, Gaussian blur and the like) with different degrees are randomly added to one picture so as to cause the picture to be seriously distorted.
The basic concept of the invention is as follows: in the noise field self-adaptation, the labels of a source domain are obtained through a low-cost labeling platform, some labels are wrong, and in order to solve the problem of labeling noise in the source domain, the method utilizes the characteristic that a deep neural network is used for fitting a noise sample after preferentially fitting a clean sample, and a sample with small loss is considered as a clean sample through analyzing each loss so as to achieve the purpose of dividing a data set into the clean source domain sample and the noise source domain sample. In order to solve the problem of inconsistent edge distribution (covariate shift) of samples in a source domain and a target domain, the invention uses the thought of self-training for reference, firstly, a model is pre-trained by using the source domain samples with accurate marks, then, pseudo marks are gradually added into the target domain samples through a marking network to participate in the training of the whole model, in addition, a target domain specific classifier which is only trained by using the target domain pseudo mark samples is additionally trained by the invention to capture the specific distinguishing characteristics of the target domain, and finally, the transfer of knowledge from the source domain to the target domain is gradually realized. In addition, the invention considers the problem of label distribution shift (label distribution shift), namely that samples of each category of a source domain and a target domain may have different quantities, and severe category imbalance may exist in the domain, so the invention adopts the rebalance sampling to the pseudo label samples to keep the training of the source domain and the target domain on each category consistent, concretely, the invention constructs two label classifiers to filter the label noise in the source domain, utilizes the characteristic of fitting the noise samples after the deep neural network is preferentially fitted to the clean samples to cluster the sample loss, the cross entropy loss generated by the clean samples is small, the cross entropy loss generated by the noise samples is large, the sample loss can be fitted to the Gaussian mixed distribution composed of relatively high loss distribution and relatively low loss distribution, and the probability that the loss of each sample belongs to the low loss distribution is the probability that the sample is the clean sample, and in order to reduce the continuous accumulation of the errors of a single model, the two mark classifiers divide the clean and noise samples for each other, the noise source domain sample and the target domain sample are utilized together in each iteration, and a reliable pseudo label is selected for the noise source domain sample and the target domain sample by judging whether the strength enhancement is consistent or not to construct a pseudo label data set. Aiming at the problem of inconsistent distribution of categories of different domains, the method carries out rebalance sampling on the pseudo labels. By the method, the problem of noise field self-adaptation and the phenomenon of category distribution offset (the category distribution offset is embodied in that each category in each domain is unbalanced and the unbalanced effect of a source domain sample and a target domain sample on each category is different) can be effectively solved, and the robustness of the field self-adaptation method under the noise condition is further improved.
The invention is described in further detail below with reference to the following figures and detailed description:
as shown in fig. 1, the robust domain adaptive image learning method based on self-training noise label correction includes the following steps:
step 1, obtaining a source domain original data set
Figure 979000DEST_PATH_IMAGE013
And a target domain data set
Figure 595926DEST_PATH_IMAGE014
。
Wherein the content of the first and second substances,D s representing source domain raw images acquired by a network platformx si And its corresponding source domain low quality mark
Figure 682831DEST_PATH_IMAGE003
The original data set of the source domain of the composition,N s representing a source domain raw data setD s Total number of samples in (c).
D t Representing the original image only by the target domainx ti The composed target domain data set is composed of,N t to representD t Number of medium target domain samples.
The source domain and target domain images can easily acquire a batch of high-quality images through an internet platform.
The annotation of the source domain image set can be obtained through a network public annotation platform, such as a crowdsourcing annotation platform; the markers obtained by such low cost are not completely accurate and therefore contain a large number of noisy markers.
When the real mark of the image has the problem of unbalanced category, the collected mark is also unbalanced, and therefore, the source domain category distribution and the target domain category distribution may have a non-uniform phenomenon.
In such cases, it is extremely challenging to implement knowledge migration from the source domain to the target domain.
Step 2, initializing various parameters including iteration timest=0, the secondtRound false mark thresholdγ tPre-training parametersN warm . Wherein the content of the first and second substances,γ tthe hyperparameter set by people represents that the upper limit of the number of the pseudo mark samples is set in each round of iterative training.
And 3, building a deep learning model and a loss function, comprising the following steps: feature extractorGTwo tag classifierC 1、C 2Target domain specific classifierC t Cross entropy loss functionL ce And a consistency loss functionL sp 。
As shown in fig. 2, the entire frame comprises four parts: feature extractor (encoder) composed of deep convolutional networkGAnd a classifier composed of three fully-connected layers and a BN (Batch Normalization) layerC 1、C 2、C t 。
Wherein the content of the first and second substances,Gis a deep convolutional neural network used for extracting the characteristics of the sample and mapping the image to a high-dimensional characteristic space.
Figure 94220DEST_PATH_IMAGE015
In order to be a clean source domain sample,
Figure 266576DEST_PATH_IMAGE016
and
Figure 421613DEST_PATH_IMAGE012
and respectively providing pseudo label sets of the source domain and the target domain which can be used after screening.
Two tag classifiers in this exampleC 1、C 2The effects of (A) are as follows:
1. in the detection stage, the original data set of the source domain is mainly subjected toD s The noise mark in the signal is detected and filtered, andD s partitioning into clean source domain samples
Figure 628604DEST_PATH_IMAGE005
And noise source domain samples
Figure 207965DEST_PATH_IMAGE007
And for detected noise source field samples
Figure 602037DEST_PATH_IMAGE007
And target domain samplesD t Predicting pseudo-marks, respectively obtained by re-balancing the samples
Figure 560766DEST_PATH_IMAGE017
、
Figure 622263DEST_PATH_IMAGE011
And participating in the next round of self-training.
2. In the training phase, for twoC 1、C 2By using
Figure 641035DEST_PATH_IMAGE005
And
Figure 787982DEST_PATH_IMAGE018
，
Figure 284823DEST_PATH_IMAGE011
the composed mixture data to train them.
C t For target domain specific classifiers, only target domain pseudo-labeled sets are used
Figure 935247DEST_PATH_IMAGE009
Training to obtain the characteristic features of the target domain without being interfered by the source domain features, and finally obtaining the target domain with good classification performanceC t And realizing the migration of the knowledge from the source domain to the target domain.
For a single picturex，GIt is first mapped into a high-dimensional depth feature space and thenC 1、C 2AndC t predicting probability of the mapped features, mapping toKProbability vector of dimensionP model And
Figure 124920DEST_PATH_IMAGE019
，Kis the number of categories.
Step 4, the original data set of the source domainD s Source domain original image inx si Input feature extractorGTo extract features in an imagef si =G(x si ) Then the original image of the source domain is processedx si Extracted source domain featuresf si And low quality marks corresponding to the original image of the source domain
Figure 493584DEST_PATH_IMAGE004
Is sent into two mark classifiersC 1、C 2In the middle ofWarm upTraining, trainingN warm And (4) wheels.
Warm upThe training means that before formal self-training, the original data set of the source domain is utilizedD s By optimizing the cross entropy loss functionL ce Simple prediction to update a modelAnd training, namely fitting the characteristics of the noise sample after preferentially fitting the clean sample according to the deep neural network, so that the model can be used as pre-training of the following self-training (step 5-step 10) through initial training, fit the clean mark without fitting the noise mark, and play a role in initializing the network parameters of the whole model.
Step 5. in the detection stage, two mark classifiers are usedC 1、C 2Sequentially and respectively detecting the marking noise in the original data set of the source domain, and mutually taking the original data set of the source domain as the opposite sideD s Into clean source domain samples and noise source domain samples.
Step 5.1, initialize noise filtering thresholdτ=0.6。
Wherein the content of the first and second substances,τthe hyper-parameter set artificially represents the boundary of whether the noise is judged to be a clean sample or not at each noise detection.
Step 5.2. willD s Original image of medium source domainx si Input feature extractorGExtracting features to obtainf si_t =G(x si )。
Wherein the content of the first and second substances,f si_t is as followstIn the self-training process, the original image of the source domainx si Input feature extractorGThe features obtained later, features extracted from each round of training in the training processf si_t All are different.
Step 5.3, all source domain original images in the step 5.2 are processedx si Extracted featuresf si_t All input to two mark classifiers in turnC 1、C 2In using two tag classifiersC 1、C 2Respectively aiming at the original image of each source domain in sequencex si Extracted featuresf si_t Performing class prediction to obtain corresponding class prediction resultC 1(f si_t )、C 2(f si_t )。
Wherein the content of the first and second substances,C 1(f si_t ) To useC 1For each source domain original imagex si Extracted featuresf si_t Performing a result of the category prediction;C 2(f si_t ) To useC 2For each source domain original imagex si Extracted featuresf si_t And (5) performing a category prediction result.
Using cross entropy loss functionL ce Calculating the class prediction results respectivelyC 1(f si_t )、C 2(f si_t ) And source domain original imagex si Corresponding source domain low quality mark
Figure 794116DEST_PATH_IMAGE004
Calculating cross entropy loss to obtain cross entropy lossl i1,l i2} i Ns 。
Wherein the content of the first and second substances,l i1is composed ofC 1(f si_t ) And source domain original imagex si Corresponding source domain low quality mark
Figure 564625DEST_PATH_IMAGE004
The cross-entropy loss of (a) is,l i2is composed ofC 2(f si_t ) And source domain original imagex si Corresponding source domain low quality mark
Figure 925200DEST_PATH_IMAGE004
Cross entropy loss of (2).
Step 5.4. Cross entropy loss for all source domain original images respectively by means of Gaussian Mixture Model (GMM)l i1,l i2} i Ns Fitting a Gaussian mixture distribution to obtain the Gaussian mixture distributionp(g|l i1)、p(g| l i2)。
Each gaussian mixture distribution consists of two gaussian distributions representing a distribution with less loss and a distribution with greater loss, respectively.
Wherein the content of the first and second substances,p(g| l i1)、p(g| l i2) Respectively two mark classifiersC 1、C 2For each source domain original imagex si ∈D s Source domain low-quality mark corresponding to category prediction
Figure 46739DEST_PATH_IMAGE004
And calculating the probability of low loss after cross entropy loss.
Fitting principle of Gaussian mixture distribution:
according to the characteristics of fitting noise samples after the clean samples are fitted preferentially by the deep neural network, the sample loss is clustered, the cross entropy loss generated by the clean samples is small, the cross entropy loss generated by the noise samples is large, and the loss of all samples can be fitted into Gaussian mixture distribution consisting of relatively high loss distribution and relatively low loss distribution. Based on the property that the deep neural network preferentially fits the clean mark, we consider that the source domain raw image with less loss is more likely to belong to a clean sample.
Step 5.5, Gaussian mixture distributionp(g| l i1)、p(g| l i2) Greater than a noise filtering thresholdτThe source domain original image of (2) is used as a clean source domain sample, and the rest source domain original image is used as a noise source domain sample.
To reduce the constant accumulation of errors in the individual models themselves, two label classifiers are used before the next round of self-trainingC 1、C 2Partitioning clean source domain samples for each other
Figure 885382DEST_PATH_IMAGE005
And noise source domain samples
Figure 775978DEST_PATH_IMAGE007
I.e. mark classifierC 1To the data partitioning result ofC 2Use, mark classifierC 2To the data partitioning result ofC 1The preparation is used.
FIG. 3 shows two tag classifiersC 1、C 2How to filter the markup noise in the source domain.
Step 6, two mark classifiers are usedC 1、C 2In turn, are noise source domain samples
Figure 307454DEST_PATH_IMAGE007
And a target domain data setD t Performing class prediction on each sample, and taking the prediction class as the class
Figure 385131DEST_PATH_IMAGE007
AndD t pseudo-labeling of each sample.
To overcome the problem of inconsistent distribution of source domain and target domain categories, the method is based onγ tFor in step 6
Figure 293044DEST_PATH_IMAGE007
AndD t is re-balanced sampled for each pseudo-labeled sample in a sample sampling ratio of each class ofγ t / KTo obtain a pseudo label setD sp ={
Figure 38146DEST_PATH_IMAGE020
，
Figure 740523DEST_PATH_IMAGE021
}。
Wherein the content of the first and second substances,Kthe number of categories is indicated and the number of categories,
Figure 571076DEST_PATH_IMAGE018
a set of pseudo-annotations of the source domain is represented,
Figure 751521DEST_PATH_IMAGE011
representing a target domain pseudo label set.
FIG. 4 is a flow chart illustrating the generation and rebalancing of sampling pseudo labels in an embodiment of the present invention.
Step 6.1. noise Source Domain samples
Figure 616709DEST_PATH_IMAGE007
The original mark is no longer trusted and is sampled with the target domainD t (itself, a non-labeled sample) constituting a set of non-labeled samples x b |x b ∈
Figure 224408DEST_PATH_IMAGE007
∪D t }. Wherein the content of the first and second substances,x b representing samples in the unlabeled sample set.
Step 6.2. samplex b Strongly enhanced version ofA(x b ) And weakly enhanced versionsα(x b ) Respectively input two tag classifiersC 1、C 2. Wherein the content of the first and second substances,A(x b ) Is to the samplex b Adding transformation and disturbance of different degrees to severely distort the picture;α(x b ) Is to the samplex b Obtained through vertical turning and translation processing.
Step 6.3. two tag classifiersC 1、C 2For weak enhanced versions respectivelyα(x b ) And strongly enhanced versionsA(x b ) Carrying out classified prediction to obtain four prediction results which are respectivelyp 1 α 、p 2 α 、p 1 A 、p 2 A . Wherein the content of the first and second substances,p 1 α for mark classifierC 1For weak enhanced versionα(x b ) Performing a prediction result of classification prediction;p 2 α for mark classifierC 2For weak enhanced versionα(x b ) And (5) carrying out a prediction result of classification prediction.p 1 A For mark classifierC 1For weak enhanced versionA (x b ) Performing a prediction result of classification prediction;p 2 A for mark classifierC 1For weak enhanced versionA (x b ) And (5) carrying out a prediction result of classification prediction. For the predicted resultp 1 α 、p 2 α Integration, i.e. addition of probability prediction vectors, is finally obtainedp α . For the predicted resultp 1 A 、p 2 A Integration, i.e. addition of probability prediction vectors, is finally obtainedp A . Wherein the content of the first and second substances,p α 、p A representing two label classifiers separatelyC 1、C 2For weak enhanced versionα(x b ) Enhanced versionA(x b ) I.e. the confidence on each class.
Step 6.4. calculate allKClass-class maximum probability prediction class:
Figure 542257DEST_PATH_IMAGE022
，
Figure 526393DEST_PATH_IMAGE023
. Wherein the content of the first and second substances,
Figure 243158DEST_PATH_IMAGE024
means all ofKThe maximum probability in a class predicts the class.
Figure 287337DEST_PATH_IMAGE025
Representing two tag classifiersC 1、C 2For weak enhanced versionα(x b ) Comprehensive pretreatmentA measured false mark;
Figure 826903DEST_PATH_IMAGE026
representing two tag classifiersC 1、C 2For strong enhancement versionA(x b ) The predicted pseudo-tags are synthesized.
Will be provided with
Figure 614731DEST_PATH_IMAGE027
=
Figure 188931DEST_PATH_IMAGE026
The prediction pseudo mark is used as a preliminary reliable pseudo mark, and the prediction probability, namely the confidence degree ranking on the prediction category is ranked from high to low; according to the confidence ranking, from each category, the sampling equal proportion isγ t / KObtaining a source domain pseudo-label set by using the pseudo-label samples with the highest quantity and confidence coefficient
Figure 404012DEST_PATH_IMAGE028
And target domain pseudo label set
Figure 430874DEST_PATH_IMAGE029
。
For example: for all the pseudo-labeled samples labeled as class k, the method ranks from high to low according to the prediction confidence of the pseudo-labeled samples on the class k, and then the sampling proportion isγ t / KA pseudo-labeled sample on class k.
Wherein the content of the first and second substances,
Figure 22392DEST_PATH_IMAGE030
、
Figure 185520DEST_PATH_IMAGE031
is the prediction probability vector of the marking network to all images with the size ofN×K。
And selecting the category with the highest prediction probability as a pseudo label for the single label-free sample.
Step 7, if the first round is adoptedIterative training, then
Figure 571502DEST_PATH_IMAGE009
=
Figure 351240DEST_PATH_IMAGE032
(ii) a If not, then,
Figure 480870DEST_PATH_IMAGE009
=
Figure 764083DEST_PATH_IMAGE009
。
because the first round of iterative training model is not trained to be mature and cannot predict accurate pseudo labels for label-free samples, the invention utilizes a source domain pseudo label set
Figure 586546DEST_PATH_IMAGE033
Training target domain specific classifiers as a first iterationC t The pseudo-tagged data set of (1).
Step 8, in the training stage, clean source domain samples are sampled
Figure 588000DEST_PATH_IMAGE005
And pseudo label setD sp Image input feature extractorGExtracting features, and inputting the extracted features and corresponding labels into two label classifiersC 1、C 2And (5) carrying out supervision training in sequence.
Wherein for clean source domain samples
Figure 255742DEST_PATH_IMAGE005
Optimizing cross entropy loss functionL ce For pseudo label setsD sp Optimizing consistency loss functionsL sp To update the feature extractorGTwo tag classifiersC 1、C 2。
Updating two tag classifiersC 1、C 2For clean source domain samples: (
Figure 393462DEST_PATH_IMAGE034
,
Figure 386826DEST_PATH_IMAGE035
)∈
Figure 609997DEST_PATH_IMAGE005
(ii) a Two tag classifierC 1、C 2To pair
Figure 347008DEST_PATH_IMAGE036
Has a prediction probability of
Figure 604814DEST_PATH_IMAGE037
(
Figure 503500DEST_PATH_IMAGE038
) Cross entropy loss functionL ce The concrete form of (A) is as follows:
Figure 213967DEST_PATH_IMAGE039
。
wherein the content of the first and second substances,Brepresenting the number of clean source field samples per small batch.
Figure 489091DEST_PATH_IMAGE040
Representing the source domain original image in a clean source domain sample,
Figure 601403DEST_PATH_IMAGE041
representing the label corresponding to the source domain image in the clean source domain sample.
Each small batch of clean source domain samples refers to clean source domain samples
Figure 936570DEST_PATH_IMAGE005
All samples in the network are evenly divided into subsets with equal sizes, and each small batch of clean source domain samples are sequentially selected and sent into the network for training.
When the data size is too large, all data cannot be sent to the network for training at one time, but all samples are divided into subsets with the same size during each iteration training, and then the subsets are sequentially selected from the subsets and sent to the network for training, so that each iteration is not a loss function for calculating all data, but a small batch of loss functions.
Therefore, the training speed of the model and the convergence speed of the model can be accelerated.
Two tag classifierC 1、C 2Re-predicting pseudo-labels for noise source domain samples and target domain samples
Figure 134333DEST_PATH_IMAGE042
And forming a pseudo-labeled sample set (x b ,
Figure 213147DEST_PATH_IMAGE043
) Using a consistency loss functionL sp The optimization model is specifically in the form of:
Figure 442616DEST_PATH_IMAGE044
；
wherein the content of the first and second substances,A(x b ) For each samplex b A strongly enhanced version of (a).P model (A(x b ) ) a presentation marker classifierC 1OrC 2For the samplex b Strongly enhanced version ofA(x b ) The class prediction of (1).H(
Figure 417525DEST_PATH_IMAGE042
,P model (A(x b ) ) is cross entropy, as follows:
H(
Figure 368164DEST_PATH_IMAGE042
,P model (A(x b )) )=
Figure 985090DEST_PATH_IMAGE045
。
step 9, pseudo labeling set of target domain
Figure 71994DEST_PATH_IMAGE012
Is input to the feature extractorGExtracting features, and inputting the extracted features and corresponding pseudo labels into a target domain specific classification networkC t Optimizing cross entropy loss functionL ce To updateG、C t 。
Specific classifiers in a target domainC t In the training phase, the loss function used in this embodiment is cross entropy lossL ce OptimizingL ce To update the target domain specific classifierC t 。
Updating target domain specific classifiersC t Using only target domain pseudo-labeled samples: (
Figure 483384DEST_PATH_IMAGE046
,
Figure 655740DEST_PATH_IMAGE047
)∈
Figure 810777DEST_PATH_IMAGE012
To train, target domain specific classifiersC t To pair
Figure 752189DEST_PATH_IMAGE046
Has a prediction probability of
Figure 334480DEST_PATH_IMAGE048
Then it crosses the entropy loss functionL ce The concrete form is as follows:
Figure 994131DEST_PATH_IMAGE049
；
wherein the content of the first and second substances,
Figure 952860DEST_PATH_IMAGE046
representing a set of pseudo labels of a target domain
Figure 14357DEST_PATH_IMAGE050
The original image of the medium target domain is,
Figure 33128DEST_PATH_IMAGE047
representing two tag classifiersC 1、C 2Is composed of
Figure 648917DEST_PATH_IMAGE046
The added pseudo-mark is added to the mark,Brepresenting the number of pseudo-labeled samples per small batch of the target domain.
Each small batch of target domain pseudo-labeled samples refers to pseudo-labeling target domains
Figure 411337DEST_PATH_IMAGE012
All samples in the target domain are uniformly divided into subsets with equal sizes, and each small batch of target domain pseudo-labeled samples are sequentially selected and sent into a network for training.
When the data size is too large, all data cannot be sent to the network for training at one time, but all samples are divided into subsets with the same size during each iteration training, and then the subsets are sequentially selected from the subsets and sent to the network for training, so that each iteration is not a loss function for calculating all data, but a small batch of loss functions.
Therefore, the training speed of the model and the convergence speed of the model can be accelerated.
Step 10, judging the current iteration timestWhether or not the maximum number of iterations has been reachedT(ii) a If it istNot reaching the maximum number of iterationsTThen, the self-training is continued by returning to the step 5,t=t+1, and updateγ t=γ 0+0.05*t(ii) a Otherwise, go to step 11;
wherein the content of the first and second substances,γ 0indicating an initialized pseudo-mark threshold.
Step 11, after the model training is completed, a feature extractor capable of extracting reliable features on the target domain is obtainedGAnd target domain specific classifier capable of performing reliable classification performance on target domain samplesC t 。
Performing a final classification prediction task, the method of the invention uses a feature extractorGExtracting features from the target domain image and inputting the extracted features into a target domain specific classification networkC t And performing category prediction.
It should be understood, however, that the description herein of specific embodiments is not intended to limit the invention to the particular forms disclosed, but on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention as defined by the appended claims.

Claims (6)

1. The robust field self-adaptive image learning method based on self-training noise label correction is characterized by comprising the following steps of:
step 1, obtaining a source domain original data set
Figure 714215DEST_PATH_IMAGE001
And a target domain data set
Figure 100196DEST_PATH_IMAGE002
；
Wherein the content of the first and second substances,D s representing source domain raw images acquired by a network platformx si And its corresponding source domain low quality mark
Figure 614354DEST_PATH_IMAGE003
The original data set of the source domain of the composition,N s representing a source domain raw data setD s Total number of medium samples;
D t representing origin only by target domainStarting imagex ti The composed target domain data set is composed of,N t to representD t The number of medium target domain samples;
step 2, initializing various parameters including iteration timest=0, the secondtRound false mark thresholdγ tPre-training parametersN warm ；
Step 3, building a deep learning model and a loss function, including a feature extractorGTwo tag classifierC 1、C 2Target domain specific classifierC t Cross entropy loss functionL ce And a consistency loss functionL sp ；
Step 4, the original data set of the source domainD s Source domain original image inx si Input feature extractorGTo extract features in an imagef si =G(x si ) Then extracting the source domain featuresf si And low quality marks corresponding to the original image of the source domain
Figure 478405DEST_PATH_IMAGE004
Is sent into two mark classifiersC 1、C 2In the middle ofWarm upTraining, trainingN warm A wheel;
step 5. in the detection stage, two mark classifiers are usedC 1、C 2Sequentially and respectively detecting the marking noise in the source domain, and mutually taking the original data sets of the source domain as the opposite sideD s Partitioning into clean source domain samples
Figure 27198DEST_PATH_IMAGE005
And noise source domain samples
Figure 584082DEST_PATH_IMAGE006
；
Step 6, two mark classifiers are usedC 1、C 2In turn, are noise source domain samples
Figure 585536DEST_PATH_IMAGE006
And a target domain data setD t Performing class prediction on each sample, and taking the prediction class as
Figure 518857DEST_PATH_IMAGE006
AndD t a pseudo-label for each sample in the set;
according toγ tFor the noise source field sample in step 6
Figure 922156DEST_PATH_IMAGE006
And a target domain data setD t In each pseudo-labeled sample, the sample sampling ratio of each category isγ t / KTo obtain a pseudo label setD sp ={
Figure 649941DEST_PATH_IMAGE007
，
Figure 138691DEST_PATH_IMAGE008
}；
Wherein the content of the first and second substances,Kthe number of categories is indicated and the number of categories,
Figure 610123DEST_PATH_IMAGE009
a set of pseudo-annotations of the source domain is represented,
Figure 602350DEST_PATH_IMAGE010
representing a target domain pseudo label set;
and 7, if the training is the first round of iterative training, then
Figure 766615DEST_PATH_IMAGE008
=
Figure 742662DEST_PATH_IMAGE007
(ii) a If not, then,
Figure 752206DEST_PATH_IMAGE008
=
Figure 130098DEST_PATH_IMAGE008
；
step 8, in the training stage, clean source domain samples are sampled
Figure 199685DEST_PATH_IMAGE005
And pseudo label setD sp Image input feature extractorGExtracting features, and inputting the extracted features and corresponding labels into two label classifiersC 1、C 2Carrying out supervision training in sequence;
for clean source domain samples
Figure 663027DEST_PATH_IMAGE005
Optimizing cross entropy loss functionL ce For pseudo label setsD sp Optimizing consistency loss functionsL sp To update the feature extractorGAnd two tag classifiersC 1、C 2；
Step 9, pseudo labeling set of target domain
Figure 476262DEST_PATH_IMAGE011
Image input feature extractorGExtracting features, and inputting the extracted features and corresponding pseudo labels into a target domain specific classification networkC t Optimizing cross entropy loss functionL ce To updateG、C t ；
Step 10, judging the current iteration timestWhether or not the maximum number of iterations has been reachedT；
If the current number of iterationstNot reaching the maximum number of iterationsTThen, the self-training is continued by returning to the step 5,t=t+1, and updateγ t=γ 0+0.05*t(ii) a Wherein the content of the first and second substances,γ 0a pseudo-mark threshold representing initialization; otherwise, go to step 11;
step 11, after the model training is finished, executing a classification prediction task, firstly using a feature extractorGExtracting features from the target domain image and inputting the extracted featuresC t And (5) performing category prediction.
2. The robust domain adaptive image learning method as recited in claim 1,
the step 5 specifically comprises the following steps:
step 5.1, initialize noise filtering thresholdτ=0.6；
Step 5.2. willD s Original image of medium source domainx si Input feature extractorGExtracting features to obtainf si_t =G(x si )；
Wherein the content of the first and second substances,f si_t is as followstIn the self-training process, the original image of the source domainx si Input feature extractorGThe characteristics obtained later;
step 5.3, all source domain original images in the step 5.2 are processedx si Extracted featuresf si_t All input to two mark classifiers in turnC 1、C 2In using two tag classifiersC 1、C 2Respectively aiming at the original image of each source domain in sequencex si Extracted featuresf si_t Performing class prediction to obtain corresponding class prediction resultC 1(f si_t )、C 2(f si_t )；
Wherein the content of the first and second substances,C 1(f si_t ) Is composed ofC 1For each source domain original imagex si Extracted featuresf si_t Performing a result of the category prediction;C 2(f si_t ) Is composed ofC 2For each source domain original imagex si Extracted featuresf si_t Performing a result of the category prediction;
using cross entropy loss functionL ce Calculating the class prediction results respectivelyC 1(f si_t )、C 2(f si_t ) And source domain original imagex si Corresponding source domain low quality mark
Figure 708661DEST_PATH_IMAGE012
Obtaining cross entropy lossl i1,l i2} i Ns ；
Wherein the content of the first and second substances,l i1to representC 1(f si_t ) And source domain original imagex si Corresponding source domain low quality mark
Figure 946219DEST_PATH_IMAGE004
The cross-entropy loss of (a) is,l i2to representC 2(f si_t ) And source domain original imagex si Corresponding source domain low quality mark
Figure 631279DEST_PATH_IMAGE004
Cross entropy loss of (d);
step 5.4, respectively carrying out comparison on all source domain original images by means of Gaussian mixture modelsx si Is a cross entropy lossl i1,l i2} i Ns Fitting a Gaussian mixture distribution to obtain the Gaussian mixture distributionp(g| l i1)、p(g| l i2)；
Each Gaussian mixture distribution consists of two Gaussian distributions which respectively represent a distribution with low loss and a distribution with high loss;
wherein，p(g| l i1)、p(g| l i2) Respectively two mark classifiersC 1、C 2For each source domain original imagex si ∈D s Source domain low-quality mark corresponding to category prediction
Figure 248205DEST_PATH_IMAGE004
Calculating the probability of low loss after cross entropy loss;
step 5.5, Gaussian mixture distributionp(g| l i1)、p(g| l i2) Middle greater than noise filtering thresholdτAs a clean source domain sample
Figure 335109DEST_PATH_IMAGE013
The residual source domain original image is used as a noise source domain sample
Figure 12078DEST_PATH_IMAGE006
；
Two tag classifierC 1、C 2Partitioning clean source domain samples for each other
Figure 184434DEST_PATH_IMAGE013
And noise source domain samples
Figure 73892DEST_PATH_IMAGE006
I.e. mark classifierC 1To the data partitioning result ofC 2Use, mark classifierC 2To the data partitioning result ofC 1The preparation is used.
3. The robust domain adaptive image learning method as recited in claim 2,
in step 6, the specific steps of generating the pseudo mark are as follows:
step 6.1. noise Source Domain samplesBook (I)
Figure 280883DEST_PATH_IMAGE006
And target domain samplesD t Forming a set of unmarked samples x b |x b ∈
Figure 128753DEST_PATH_IMAGE006
∪D t }；
Wherein the content of the first and second substances,x b representing samples in the unlabeled sample set;
step 6.2. samplex b Strongly enhanced version ofA(x b ) And weakly enhanced versionsα(x b ) Are inputted separatelyC 1、C 2；
Wherein the content of the first and second substances,A(x b ) Is a samplex b Adding transformation and disturbance of different degrees to severely distort the picture;
α(x b ) Is to the samplex b Obtained by vertical turning and translation processing;
step 6.3. two tag classifiersC 1、C 2For weak enhanced versions respectivelyα(x b ) And strongly enhanced versionsA(x b ) Carrying out classified prediction to obtain four prediction results which are respectivelyp 1 α 、p 2 α 、p 1 A 、p 2 A ；
Wherein the content of the first and second substances,p 1 α for mark classifierC 1For weak enhanced versionα(x b ) Performing a prediction result of classification prediction;p 2 α for mark classifierC 2For weak enhanced versionα(x b ) Performing a prediction result of classification prediction;
p 1 A for mark classifierC 1For weak enhanced versionA (x b ) Performing a prediction result of classification prediction;p 2 A for mark classifierC 1For weak enhanced versionA (x b ) Performing a prediction result of classification prediction;
for the predicted resultp 1 α 、p 2 α Integration, i.e. addition of probability prediction vectors, is finally obtainedp α ；
For the predicted resultp 1 A 、p 2 A Integration, i.e. addition of probability prediction vectors, is finally obtainedp A ；
Wherein the content of the first and second substances,p α 、p A representing two label classifiers separatelyC 1、C 2For weak enhanced versionα(x b ) Enhanced versionA(x b ) The overall predicted class outcome of (a), i.e., confidence in each class;
step 6.4. calculate allKClass-class maximum probability prediction class:
Figure 788405DEST_PATH_IMAGE014
，
Figure 747133DEST_PATH_IMAGE015
；
wherein the content of the first and second substances,
Figure 543051DEST_PATH_IMAGE016
means all ofKPredicting the category of the maximum probability in the category;
Figure 561823DEST_PATH_IMAGE017
representing two tag classifiersC 1、C 2For weak enhanced versionα(x b ) Pseudo-labeling for comprehensive prediction;
Figure 708770DEST_PATH_IMAGE018
representing two tag classifiersC 1、C 2For strong enhancement versionA(x b ) Pseudo-labeling for comprehensive prediction;
will be provided with
Figure 471190DEST_PATH_IMAGE019
=
Figure 121614DEST_PATH_IMAGE018
The prediction pseudo mark is used as a preliminary reliable pseudo mark, and the prediction probability, namely the confidence degree ranking on the prediction category is ranked from high to low; according to the confidence ranking, from each category, the sampling equal proportion isγ t / KObtaining a source domain pseudo-label set by using the pseudo-label samples with the highest quantity and confidence coefficient
Figure 45708DEST_PATH_IMAGE020
And target domain pseudo label set
Figure 679951DEST_PATH_IMAGE021
。
4. The robust domain adaptive image learning method as recited in claim 1,
the feature extractorGIs a feature extractor consisting of a deep convolutional network; two tag classifierC 1、C 2And a target domain specific classifierC t All are classifiers composed of three fully-connected layers and a normalization layer.
5. The robust domain adaptive image learning method as recited in claim 3,
in the training phase, optimizingL ce 、L sp To update two tag classifiersC 1、C 2；
Updating two tag classifiersC 1、C 2For clean source domain samples: (
Figure 980483DEST_PATH_IMAGE022
,
Figure 16572DEST_PATH_IMAGE023
)∈
Figure 111567DEST_PATH_IMAGE005
Two tag classifierC 1、C 2For images in clean source domain samples
Figure 967527DEST_PATH_IMAGE022
Has a prediction probability of
Figure 71749DEST_PATH_IMAGE024
(
Figure 696766DEST_PATH_IMAGE025
) Cross entropy loss functionL ce The concrete form of (A) is as follows:
Figure 228241DEST_PATH_IMAGE026
；
wherein the content of the first and second substances,Brepresenting the number of clean source domain samples per small batch,Krepresenting a category total;
each small batch of clean source domain samples refers to clean source domain samples
Figure 571498DEST_PATH_IMAGE013
In which all samples are evenly divided into subsets each having equal sizeThen, sequentially selecting each small batch of clean source domain samples, and sending the small batch of clean source domain samples into a network for training;
Figure 479411DEST_PATH_IMAGE027
representing the source domain original image in a clean source domain sample,
Figure 224513DEST_PATH_IMAGE028
a mark corresponding to the source domain image in the clean source domain sample is represented;
two tag classifierC 1、C 2Re-predicting pseudo-labels for noise source domain samples and target domain samples
Figure 926890DEST_PATH_IMAGE029
And forming a pseudo-labeled sample set (x b ,
Figure 488934DEST_PATH_IMAGE030
) Using a consistency loss functionL sp The optimization model is specifically in the form of:
Figure 934959DEST_PATH_IMAGE031
；
wherein the content of the first and second substances,A(x b ) For each samplex b A strongly enhanced version of (c);
P model (A(x b ) ) a presentation marker classifierC 1OrC 2For the samplex b Strongly enhanced version ofA(x b ) Predicting the category of (1);
H(
Figure 534567DEST_PATH_IMAGE032
,P model (A(x b ) ) is cross entropy, as follows:
H(
Figure 407845DEST_PATH_IMAGE030
,P model (A(x b )) )=
Figure 725694DEST_PATH_IMAGE033
。
6. the robust domain adaptive image learning method as recited in claim 3,
in the training phase, optimizingL ce To update the target domain specific classifier;
updating target domain specific classifiersC t Using only target domain pseudo-labeled samples: (
Figure 709831DEST_PATH_IMAGE034
,
Figure 429525DEST_PATH_IMAGE035
)∈
Figure 208125DEST_PATH_IMAGE008
To train, target domain specific classifiersC t For images
Figure 13270DEST_PATH_IMAGE034
Has a prediction probability of
Figure 535518DEST_PATH_IMAGE036
Then it crosses the entropy loss functionL ce The concrete form is as follows:
Figure 109719DEST_PATH_IMAGE037
；
wherein the content of the first and second substances,
Figure 324800DEST_PATH_IMAGE038
representing a set of pseudo labels of a target domain
Figure 351662DEST_PATH_IMAGE021
A middle target domain original image;
Figure 943180DEST_PATH_IMAGE035
representing two tag classifiersC 1、C 2Is composed of
Figure 371887DEST_PATH_IMAGE039
The added pseudo-mark is added to the label,Brepresenting the number of pseudo-labeled samples per small batch of the target domain,Krepresenting a category total;
each small batch of target domain pseudo-labeled samples refers to pseudo-labeling target domains
Figure 757869DEST_PATH_IMAGE021
All samples in the target domain are uniformly divided into subsets with equal sizes, and each small batch of target domain pseudo-labeled samples are sequentially selected and sent into a network for training.
CN202210221128.5A 2022-03-09 2022-03-09 Robust field adaptive image learning method based on self-training noise label correction Active CN114283287B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210221128.5A CN114283287B (en) 2022-03-09 2022-03-09 Robust field adaptive image learning method based on self-training noise label correction

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210221128.5A CN114283287B (en) 2022-03-09 2022-03-09 Robust field adaptive image learning method based on self-training noise label correction

Publications (2)

Publication Number Publication Date
CN114283287A true CN114283287A (en) 2022-04-05
CN114283287B CN114283287B (en) 2022-05-06

Family

ID=80882312

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210221128.5A Active CN114283287B (en) 2022-03-09 2022-03-09 Robust field adaptive image learning method based on self-training noise label correction

Country Status (1)

Country Link
CN (1) CN114283287B (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114723994A (en) * 2022-04-18 2022-07-08 中国矿业大学 Hyperspectral image classification method based on dual-classifier confrontation enhancement network
CN114998602A (en) * 2022-08-08 2022-09-02 中国科学技术大学 Domain adaptive learning method and system based on low confidence sample contrast loss
CN115331065A (en) * 2022-10-13 2022-11-11 南京航空航天大学 Robust noise multi-label image learning method based on decoder iterative screening
CN115331088A (en) * 2022-10-13 2022-11-11 南京航空航天大学 Robust learning method based on class labels with noise and imbalance
CN115496972A (en) * 2022-11-15 2022-12-20 杭州涿溪脑与智能研究所 Industrial field self-adaption method based on data mixing
CN117132841A (en) * 2023-10-26 2023-11-28 之江实验室 Domain self-adaptive image classification method and device for conservation and progression
CN117848588A (en) * 2024-03-07 2024-04-09 青岛天一红旗软控科技有限公司 Mechanical balance self-adaptive test method
CN118097319A (en) * 2024-04-29 2024-05-28 南京航空航天大学 Image classification method with unseen class and noise labels in online stream data

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110837850A (en) * 2019-10-23 2020-02-25 浙江大学 Unsupervised domain adaptation method based on counterstudy loss function
US20200130177A1 (en) * 2018-10-29 2020-04-30 Hrl Laboratories, Llc Systems and methods for few-shot transfer learning
CN111368977A (en) * 2020-02-28 2020-07-03 交叉信息核心技术研究院(西安)有限公司 Enhanced data enhancement method for improving accuracy and robustness of convolutional neural network
WO2020159638A1 (en) * 2019-01-30 2020-08-06 Hrl Laboratories, Llc System and method for unsupervised domain adaptation via sliced-wasserstein distance
CN112232241A (en) * 2020-10-22 2021-01-15 华中科技大学 Pedestrian re-identification method and device, electronic equipment and readable storage medium
CN112287994A (en) * 2020-10-26 2021-01-29 北京嘀嘀无限科技发展有限公司 Pseudo label processing method, device, equipment and computer readable storage medium
CN112906606A (en) * 2021-03-05 2021-06-04 南京航空航天大学 Domain-adaptive pedestrian re-identification method based on mutual divergence learning
US20210217405A1 (en) * 2020-01-10 2021-07-15 International Business Machines Corporation Implementing a domain adaptive semantic role labeler
CN113344044A (en) * 2021-05-21 2021-09-03 北京工业大学 Cross-species medical image classification method based on domain self-adaptation
CN113378981A (en) * 2021-07-02 2021-09-10 湖南大学 Noise scene image classification method and system based on domain adaptation
CN113807420A (en) * 2021-09-06 2021-12-17 湖南大学 Domain self-adaptive target detection method and system considering category semantic matching

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200130177A1 (en) * 2018-10-29 2020-04-30 Hrl Laboratories, Llc Systems and methods for few-shot transfer learning
WO2020159638A1 (en) * 2019-01-30 2020-08-06 Hrl Laboratories, Llc System and method for unsupervised domain adaptation via sliced-wasserstein distance
CN113316790A (en) * 2019-01-30 2021-08-27 赫尔实验室有限公司 System and method for unsupervised domain adaptation via SLICED-WASSERSTEIN distance
CN110837850A (en) * 2019-10-23 2020-02-25 浙江大学 Unsupervised domain adaptation method based on counterstudy loss function
US20210217405A1 (en) * 2020-01-10 2021-07-15 International Business Machines Corporation Implementing a domain adaptive semantic role labeler
CN111368977A (en) * 2020-02-28 2020-07-03 交叉信息核心技术研究院(西安)有限公司 Enhanced data enhancement method for improving accuracy and robustness of convolutional neural network
CN112232241A (en) * 2020-10-22 2021-01-15 华中科技大学 Pedestrian re-identification method and device, electronic equipment and readable storage medium
CN112287994A (en) * 2020-10-26 2021-01-29 北京嘀嘀无限科技发展有限公司 Pseudo label processing method, device, equipment and computer readable storage medium
CN112906606A (en) * 2021-03-05 2021-06-04 南京航空航天大学 Domain-adaptive pedestrian re-identification method based on mutual divergence learning
CN113344044A (en) * 2021-05-21 2021-09-03 北京工业大学 Cross-species medical image classification method based on domain self-adaptation
CN113378981A (en) * 2021-07-02 2021-09-10 湖南大学 Noise scene image classification method and system based on domain adaptation
CN113807420A (en) * 2021-09-06 2021-12-17 湖南大学 Domain self-adaptive target detection method and system considering category semantic matching

Non-Patent Citations (8)

* Cited by examiner, † Cited by third party
Title
CHEN WEI等: "CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning", 《COMPUTER VISION AND PATTERN RECOGNITION》 *
QIANGGUO JIN等: "Domain adaptation based self-correction model for COVID-19 infection segmentation in CT images", 《ARXIV》 *
XIYU YU等: "Label-Noise Robust Domain Adaptation", 《PROCEEDINGS OF THE 37TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING》 *
YITING CHENG等: "Dual Path Learning for Domain Adaptation of Semantic Segmentation", 《COMPUTER VISION FOUNDATION》 *
付家慧: "深度迁移学习算法及其应用研究", 《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》 *
吴涛: "领域自适应方法在图像分类上的研究与应用", 《万方在线》 *
杨艺等: "一种基于自训练的众包标记噪声纠正算法", 《自动化学报》 *
程康明等: "一种自训练框架下的三优选半监督回归算法", 《智能系统学报》 *

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114723994A (en) * 2022-04-18 2022-07-08 中国矿业大学 Hyperspectral image classification method based on dual-classifier confrontation enhancement network
CN114998602A (en) * 2022-08-08 2022-09-02 中国科学技术大学 Domain adaptive learning method and system based on low confidence sample contrast loss
CN114998602B (en) * 2022-08-08 2022-12-30 中国科学技术大学 Domain adaptive learning method and system based on low confidence sample contrast loss
CN115331065A (en) * 2022-10-13 2022-11-11 南京航空航天大学 Robust noise multi-label image learning method based on decoder iterative screening
CN115331088A (en) * 2022-10-13 2022-11-11 南京航空航天大学 Robust learning method based on class labels with noise and imbalance
CN115496972A (en) * 2022-11-15 2022-12-20 杭州涿溪脑与智能研究所 Industrial field self-adaption method based on data mixing
CN115496972B (en) * 2022-11-15 2023-04-07 杭州涿溪脑与智能研究所 Industrial field self-adaption method based on data mixing
CN117132841A (en) * 2023-10-26 2023-11-28 之江实验室 Domain self-adaptive image classification method and device for conservation and progression
CN117132841B (en) * 2023-10-26 2024-03-29 之江实验室 Domain self-adaptive image classification method and device for conservation and progression
CN117848588A (en) * 2024-03-07 2024-04-09 青岛天一红旗软控科技有限公司 Mechanical balance self-adaptive test method
CN117848588B (en) * 2024-03-07 2024-06-04 青岛天一红旗软控科技有限公司 Mechanical balance self-adaptive test method
CN118097319A (en) * 2024-04-29 2024-05-28 南京航空航天大学 Image classification method with unseen class and noise labels in online stream data

Also Published As

Publication number Publication date
CN114283287B (en) 2022-05-06

Similar Documents

Publication Publication Date Title
CN114283287B (en) Robust field adaptive image learning method based on self-training noise label correction
WO2021134871A1 (en) Forensics method for synthesized face image based on local binary pattern and deep learning
CN110443143B (en) Multi-branch convolutional neural network fused remote sensing image scene classification method
CN108648191B (en) Pest image recognition method based on Bayesian width residual error neural network
CN111160553B (en) Novel field self-adaptive learning method
CN112733965B (en) Label-free image classification method based on small sample learning
CN108416382B (en) Web image training convolutional neural network method based on iterative sampling and one-to-many label correction
CN110781921A (en) Depth residual error network and transfer learning-based muscarinic image identification method and device
CN113076994B (en) Open-set domain self-adaptive image classification method and system
CN113361566B (en) Method for migrating generative confrontation network by using confrontation learning and discriminant learning
CN115331088B (en) Robust learning method based on class labels with noise and imbalance
CN114842267A (en) Image classification method and system based on label noise domain self-adaption
CN113780242A (en) Cross-scene underwater sound target classification method based on model transfer learning
CN113297988A (en) Object attitude estimation method based on domain migration and depth completion
CN114139616A (en) Unsupervised domain adaptive target detection method based on uncertainty perception
CN111028203A (en) CNN blind image quality evaluation method based on significance
CN114943965A (en) Unsupervised domain self-adaptive remote sensing image semantic segmentation method based on course learning
CN113869463B (en) Long tail noise learning method based on cross enhancement matching
CN112883931A (en) Real-time true and false motion judgment method based on long and short term memory network
CN113989256A (en) Detection model optimization method, detection method and detection device for remote sensing image building
CN111310820A (en) Foundation meteorological cloud chart classification method based on cross validation depth CNN feature integration
CN115331065B (en) Robust noise multi-label image learning method based on decoder iterative screening
CN115205275A (en) Surface defect detection method based on deep learning algorithm
CN115223033A (en) Synthetic aperture sonar image target classification method and system
CN113553917B (en) Office equipment identification method based on pulse transfer learning

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant