CN115471739A - Cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning - Google Patents

Cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning Download PDF

Info

Publication number
CN115471739A
CN115471739A CN202210927707.1A CN202210927707A CN115471739A CN 115471739 A CN115471739 A CN 115471739A CN 202210927707 A CN202210927707 A CN 202210927707A CN 115471739 A CN115471739 A CN 115471739A
Authority
CN
China
Prior art keywords
domain
image
target
target domain
class
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.)
Pending
Application number
CN202210927707.1A
Other languages
Chinese (zh)
Inventor
王思远
侯东阳
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.)
Central South University
Original Assignee
Central South University
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 Central South University filed Critical Central South University
Priority to CN202210927707.1A priority Critical patent/CN115471739A/en
Publication of CN115471739A publication Critical patent/CN115471739A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/55—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/761—Proximity, similarity or dissimilarity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
    • G06V10/7753—Incorporation of unlabelled data, e.g. multiple instance learning [MIL]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Library & Information Science (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

The invention relates to a cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning, which comprises the following steps: a) Acquiring a remote sensing image and constructing input data; b) Constructing a loss function based on self-supervision contrast learning and combining a known sample and an unknown sample of a target domain image, constructing a depth domain adaptive learning network, and training the depth domain adaptive learning network by using input data and the loss function; c) Classifying the target domain images by using a depth domain adaptive learning network, extracting target image feature vectors of the target domain images to construct a feature database, extracting query image feature vectors of the target domain query images, calculating Euclidean distances between the query image feature vectors and the target image feature vectors in the feature database, and selecting a required retrieval target based on the Euclidean distances. The cross-domain remote sensing scene classification and retrieval method based on the self-supervision contrast learning can still have good cross-domain classification and retrieval precision under the condition that unknown classes exist in the target domain.

Description

Cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning
Technical Field
The invention relates to the technical field of optical remote sensing image retrieval, in particular to a cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning.
Background
In recent years, the progress of earth observation technology provides more and more high-resolution remote sensing images for human beings, brings huge opportunities for the remote sensing field, and greatly promotes the application of the remote sensing images in different fields. The remote sensing image scene classification and retrieval are basic tasks in the field of remote sensing image interpretation, can quickly and accurately understand and manage remote sensing image data, and play an important role in the fields of environment monitoring, land utilization, visual navigation and the like.
The deep Convolutional Neural Networks (CNNs) developed in recent years have strong feature fitting capability, and exhibit great superiority in remote sensing scene classification and retrieval tasks. The general process is that firstly, a main network pre-trained by a general large-scale image data set (such as ImageNet) is finely adjusted on a remote sensing image data set, and then the activation output of the network is extracted to be used as an image feature representation for retrieval or classification.
However, most of the existing CNN-based methods are supervised, and it is usually assumed that the training set and the test set share the same data distribution, and in practical applications, due to the difference of imaging conditions such as sensors, shooting angles, shooting weather, etc., the feature of the same type has a huge difference in different data distributions, which is called data migration, when there is data migration between the training set and the test set, the generalization effect of the model on the test set is poor, and re-labeling the test set is time-consuming, labor-consuming and impractical; in addition, most of existing domain adaptation remote sensing scene classification or retrieval methods are proposed for closed set scenes, that is, a target domain and a source domain share the same label space, and in a complex actual scene, the assumption is easily violated because the class of the source domain is often incomplete, the source domain cannot cover all classes, and the target domain may contain class samples which are not shared by the source domain.
In view of the above, it is necessary to design a cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning.
Disclosure of Invention
The invention aims to provide a cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning, which can still have good classification and retrieval precision of a target domain under the condition that the target domain has unknown classes.
In order to solve the technical problem, the invention provides a cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning, which comprises the following steps:
a) Acquiring a remote sensing image, and dividing a source domain image and a target domain image of the remote sensing image to construct input data;
b) Constructing a loss function based on self-supervision contrast learning and combined with the known class and the unknown class of the target domain image, constructing a depth domain adaptive learning network, and training the depth domain adaptive learning network by using the input data and the loss function;
c) Classifying the target domain images by using the trained depth domain adaptive learning network, extracting target image feature vectors of the target domain images to construct a feature database, extracting query image feature vectors of the target domain query images, calculating Euclidean distances between the query image feature vectors and all the target image feature vectors in the feature database, arranging according to the Euclidean distances, and obtaining the required retrieval target according to a set Euclidean distance range.
Further, the step of constructing the input data comprises: extracting from the data set of the remote sensing imageA stem image {1,2, …, N }, and constructing the source domain image
Figure BDA0003780275380000021
The source domain image comprises n s Image with label source domain
Figure BDA0003780275380000022
Representing annotated source domain images
Figure BDA0003780275380000023
The corresponding label, wherein,
Figure BDA0003780275380000031
representing the label space of the image with the labeling source domain, and C representing the total number of categories of the image with the labeling source domain; the target domain image is
Figure BDA0003780275380000032
The target domain image comprises n t Label-free target domain image
Figure BDA0003780275380000033
Wherein the target domain image
Figure BDA0003780275380000034
The label space of (a) is: {1,2, …, C +1}, C +1 representing the unknown class of the label-free target domain image.
Further, the deep domain adaptive learning network comprises a plurality of feature coding networks f (-), a plurality of contrast learning networks g (-), and a plurality of classifiers c (-).
Further, the feature coding network f (-) is a depth residual network with a full connection layer removed, and an average pooling layer of the depth residual network is replaced by a bottleneck layer.
Further, the contrast learning network g (-) is a perceptron with a ReLU (modified linear unit) activation function.
Further, the classifier c (-) is a fully connected network, and the output dimension of the classifier c (-) is consistent with the class number of the target domain image.
Further, the constructing step of the loss function includes:
b11 Construct source domain classification loss: and carrying out supervised learning on the source domain image, and calculating the classification accuracy by adopting cross entropy loss:
Figure BDA0003780275380000035
wherein L is softmax In order to classify the function of the loss,
Figure BDA0003780275380000036
a source domain annotated image representing the source domain image
Figure BDA0003780275380000037
True class distribution, function
Figure BDA0003780275380000038
A source domain weakly enhanced sample class probability distribution representing the classifier output,
Figure BDA0003780275380000039
a collection of label exemplars representing an annotated image in a source domain;
b12 Construct the self-supervised contrast loss: constructing a target domain strong enhancement sample of the target domain image
Figure BDA00037802753800000310
And target domain weakly enhanced samples
Figure BDA00037802753800000311
To calculate the contrast loss L ssl ：
Figure BDA00037802753800000312
Wherein sim (-) is the similarity measure function, θ is the scaling factor, A ∈ {0,1} is an indication function for evaluating whether k equals j, B represents the number of samples selected by one training;
b13 Construct a known class identification penalty as:
Figure BDA0003780275380000041
where μ represents the proportion of samples within a training run that meet the selection requirements for a known class threshold, H (-) represents the cross entropy loss,
Figure BDA0003780275380000042
for weakly enhancing samples from the target domain
Figure BDA0003780275380000043
The collected set of the target domain known pseudo labels obtained through screening, ind represents the target domain weak enhancement sample
Figure BDA00037802753800000417
The category to which the known pseudo label belongs after screening, and ind epsilon {1,2, …, C },
Figure BDA0003780275380000044
representing strongly enhanced samples of the target domain
Figure BDA0003780275380000045
Is determined based on the predicted class probability distribution of (c),
Figure BDA0003780275380000046
a collection of labeled exemplars representing strongly enhanced exemplars of the target domain;
b14 Construct unknown class identification loss: consistency classification loss L of unknown class identification loss as high-confidence unknown class sample unknown ：
Figure BDA0003780275380000047
Wherein, the first and the second end of the pipe are connected with each other,
Figure BDA0003780275380000048
for weakly enhancing samples from the target domain
Figure BDA0003780275380000049
Screening the obtained collection of the unknown pseudo labels of the target domain,
Figure BDA00037802753800000410
representing strongly enhanced samples of the target domain
Figure BDA00037802753800000411
A predicted class probability distribution of (a);
b15 ) the constructed total loss function L is:
L＝L softmax +αL ssl +βL known +γL unknown
where α, β and γ are parameters that balance the optimization objectives of the model.
Further, the target domain weakly enhances samples
Figure BDA00037802753800000412
By comparing the label-free target domain image
Figure BDA00037802753800000413
Obtaining the product by random cutting and turning; the target domain strongly enhanced sample
Figure BDA00037802753800000414
By comparing the label-free target domain image
Figure BDA00037802753800000415
Obtaining by using a random enhancement method; the source domain weakly enhances the sample by matching the annotated source domain image
Figure BDA00037802753800000416
And obtaining the target by random cutting and overturning.
Further, the training step of the deep domain adaptive learning network comprises:
b21 The source domain weakly enhanced sample and the target domain weakly enhanced sample
Figure BDA0003780275380000051
And target domain strongly enhanced samples
Figure BDA0003780275380000052
Inputting into the feature coding network f (-) to respectively obtain the source domain features
Figure BDA0003780275380000053
Target domain weakly enhanced image features
Figure BDA0003780275380000054
And strong enhancement of image features in the target domain
Figure BDA0003780275380000055
B22 Weakly enhancing the target domain image features
Figure BDA0003780275380000056
And the target domain strongly enhances image features
Figure BDA0003780275380000057
Inputting the contrast learning network g (-) to obtain the embedded characteristics of the projected target domain weak enhanced image
Figure BDA0003780275380000058
And strong enhancement of image embedding characteristics in the target domain
Figure BDA0003780275380000059
To calculate the contrast loss L ssl ；
B23 Characterize the source domain
Figure BDA00037802753800000510
The target domain weakly enhances image features
Figure BDA00037802753800000511
And the target domain strongly enhances image features
Figure BDA00037802753800000512
Inputting the classifier c (-) to respectively obtain the source domain weakly enhanced sample class probability distribution predicted by the classifier
Figure BDA00037802753800000513
The target domain weakly enhanced sample class probability distribution
Figure BDA00037802753800000514
And the target domain strongly enhances the sample class probability distribution
Figure BDA00037802753800000515
B24 Weakly enhancing sample class probability distribution to the source domain
Figure BDA00037802753800000516
Based on the classification loss function L softmax Calculating the classification loss of the source domain;
b25 Weakly enhancing sample class probability distribution to the target domain
Figure BDA00037802753800000517
Firstly, finding the category of the maximum prediction probability, comparing the probability value of the category with a preset predefined threshold tau, abandoning the samples smaller than tau, reserving the samples larger than tau as pseudo label samples, and taking the category of the maximum prediction probability as a known hard label, wherein the screening formula is as follows:
Figure BDA00037802753800000518
wherein, the first and the second end of the pipe are connected with each other,
Figure BDA00037802753800000519
to represent
Figure BDA00037802753800000520
A category in which the maximum prediction probability that satisfies a threshold condition is located;
b26 Using the target domain weakly enhanced samples
Figure BDA00037802753800000521
Known pseudo-label
Figure BDA00037802753800000522
As strong enhancement samples of the corresponding target domain
Figure BDA00037802753800000523
Calculates the target domain strong enhancement samples
Figure BDA00037802753800000524
Said known class of (1) identifies a loss L known ；
B27 Selecting the target domain weakly enhanced sample class probability distribution
Figure BDA00037802753800000525
And taking the sample with lower confidence level as a candidate unknown sample, wherein the specific selection formula is as follows:
Figure BDA0003780275380000061
wherein
Figure BDA0003780275380000062
For the preliminarily screened candidate unknown samples, t l Selecting a threshold value for the candidate sample, selecting a sample predicted that the probability of the unknown class is higher than the set unknown class sample selection threshold value as an unknown class sample,
Figure BDA0003780275380000063
wherein
Figure BDA0003780275380000064
Is the candidate sample
Figure BDA0003780275380000065
Probability of prediction as unknown class, t uk A threshold value is chosen for the unknown class sample,
Figure BDA0003780275380000066
unknown pseudo-label for target domain;
b28 With the target domain unknown class pseudo-tag
Figure BDA0003780275380000067
As a strongly enhanced sample of the target domain
Figure BDA0003780275380000068
Calculating a consistent classification loss L of the unknown class samples unknown And obtaining the total loss function L, and updating the parameters of the deep domain adaptive learning network.
Further, the step of obtaining the retrieval target is:
c21 Extracting the query image feature vector based on the trained feature coding network;
c22 Computing Euclidean distances between the query image feature vector and each target image feature vector in the feature database one by one;
c23 According to the Euclidean distance between the target image feature vector and the query image feature vector, sorting the target image feature vectors to obtain the retrieval target corresponding to the target image feature vectors.
According to the technical scheme, in the cross-domain remote sensing scene classification and retrieval method of the self-supervision contrast learning, input data are constructed firstly and comprise data of a source domain image and data of a target domain image, wherein the data of the source domain image is marked data, the data of the target domain image is unmarked data, the constructed input data are correspondingly enhanced, then the enhanced data of the source domain image and the data of the target domain image are input into a corresponding feature coding network, an output result is compared with the input data, a loss function is constructed on the basis of the self-supervision contrast learning by combining a known class and an unknown class of the target domain image, so that network parameters of the feature coding network can be adjusted on the basis of the loss function, the influence of the unknown class samples existing in the target domain on the feature coding network can be reduced, and the trained depth domain adaptive learning network has a better effect when the data containing the unknown class samples are classified or retrieved.
Further advantages of the present invention, as well as the technical effects of preferred embodiments, are further described in the following detailed description.
Drawings
FIG. 1 is a flow chart of the cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning according to the present invention;
FIG. 2 is a schematic diagram illustrating the principle of the cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning according to the present invention;
FIG. 3 is a schematic diagram of a training process of a deep domain adaptive learning network in the cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning according to the present invention;
FIG. 4 is a schematic diagram of a retrieval process in the cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning according to the present invention;
FIG. 5 is a classification confusion matrix adapted to a counterdiscrimination domain in the cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning according to the present invention;
FIG. 6 is a classification confusion matrix of batch singular value constraints in the cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning according to the present invention;
FIG. 7 is a classification confusion matrix of a depth domain adaptive network in the cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning according to the present invention;
FIG. 8 is a classification confusion matrix for a back propagation open set domain adaptation in the cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning according to the present invention;
FIG. 9 is a classification confusion matrix of the cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning.
Detailed Description
The following describes in detail embodiments of the present invention with reference to the drawings. It should be understood that the detailed description and specific examples, while indicating the present invention, are given by way of illustration and explanation only, not limitation.
As shown in fig. 1 and fig. 2, as an embodiment of the method for classifying and retrieving cross-domain remote sensing scenes based on self-supervised contrast learning provided by the present invention, the method includes the following steps:
a) Acquiring a remote sensing image, and dividing a source domain image and a target domain image of the remote sensing image to construct input data;
b) Constructing a loss function based on self-supervision contrast learning and combining a known sample and an unknown sample of a target domain image, constructing a depth domain adaptive learning network, and training the depth domain adaptive learning network by using input data and the loss function;
c) Classifying the target domain images by using a trained depth domain adaptive learning network, extracting target image feature vectors of the target domain images to construct a feature database, extracting query image feature vectors of the target domain query images, calculating Euclidean distances between the query image feature vectors and all target image feature vectors in the feature database, arranging according to the Euclidean distances, and obtaining a required retrieval target according to a set Euclidean distance range.
Specifically, in an embodiment of the cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning provided by the present invention, the input data construction step includes: extracting a plurality of images {1,2, …, N } from a data set of remote sensing images to construct source domain images
Figure BDA0003780275380000081
The source domain image contains n s Image with label source domain
Figure BDA0003780275380000082
Representing annotated source domain images
Figure BDA0003780275380000083
The corresponding label, wherein,
Figure BDA0003780275380000084
Figure BDA0003780275380000085
c, representing the label space of the image with the labeling source domain, and representing the total number of categories of the image with the labeling source domain; the target domain image is
Figure BDA0003780275380000086
The target domain image contains n t Non-annotated target domain image
Figure BDA0003780275380000087
Wherein the target domain image
Figure BDA0003780275380000088
The label space of (a) is: {1,2, …, C +1}, C +1 representing the unknown class of the label-free target domain image.
Further, in an embodiment of the cross-domain remote sensing scene classification and retrieval method based on the self-supervision contrast learning provided by the present invention, as shown in fig. 3 and fig. 4, the deep domain adaptive learning network includes a plurality of feature coding networks f (·), a plurality of contrast learning networks g (·), and a plurality of classifiers c (·); the feature coding network is a depth residual error network with a full connection layer removed, the last average pooling layer is replaced by a bottleneck layer, and 256-dimensional feature vectors are output; the contrast learning network g (-) is a perceptron with a ReLU (modified Linear Unit) activation function; the classifier C (-) is a fully-connected network, the input of the classifier C (-) is a 256-dimensional feature vector, and the output dimension of the classifier C (-) is consistent with the number of classes of the target domain image (namely, probability distribution of {1,2, …, C, C +1} classes).
Further, in an embodiment of the cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning provided by the present invention, the step of constructing the loss function includes:
b11 Construct source domain classification loss: because the source domain images are semantically labeled (namely, the source domain images are labeled), supervised learning can be carried out on the source domain images, and the classification accuracy is calculated by adopting cross entropy loss:
Figure BDA0003780275380000091
wherein L is softmax In order to classify the function of the loss,
Figure BDA0003780275380000092
annotated image of source domain representing image of source domain
Figure BDA0003780275380000093
True class distribution, function of
Figure BDA0003780275380000094
A source domain weakly enhanced sample class probability distribution representing the classifier output,
Figure BDA0003780275380000095
a collection of labels representing source domain annotated images;
b12 Construct an unsupervised contrast loss: self-supervised contrast learning is to learn a representation by maximizing information between different views of the data, and in particular, by encouraging two views from the same image of the target domain (i.e., a strongly enhanced view and a weakly enhanced view) to be similar, and two views from different images to be dissimilar, to learn more discriminative image features, and thus, a strongly enhanced sample of the target domain that can construct an image of the target domain
Figure BDA0003780275380000096
And target domain weakly enhanced samples
Figure BDA0003780275380000097
To calculate the contrast loss L ssl ：
Figure BDA0003780275380000098
Wherein sim (-) is the similarity measure function, θ is the scaling factor, A ∈ {0,1} is an indication function for evaluating whether k equals j, B represents the number of samples selected by one training; in particular, the target domain weakly enhances the samples
Figure BDA0003780275380000101
Is formed by the image of the unmarked target domain
Figure BDA0003780275380000102
Obtaining the product by random cutting and overturning; target domain strongly enhanced samples
Figure BDA0003780275380000103
Is formed by the image of the target domain without marking
Figure BDA0003780275380000104
Obtaining by using a random enhancement method;
b13 Construct the known class identification loss as:
Figure BDA0003780275380000105
wherein, mu represents the sample proportion meeting the selection requirement of the threshold value of the known class in one training, H (-) represents the cross entropy loss,
Figure BDA0003780275380000106
for weakly enhancing samples from the target domain
Figure BDA0003780275380000107
The collected set of the target domain known pseudo labels is obtained through screening, and ind represents a target domain weak enhancement sample
Figure BDA0003780275380000108
The category to which the pseudo label belongs after being screened by the known class, and ind belongs to {1,2, …, C },
Figure BDA0003780275380000109
representing strongly enhanced samples of a target domain
Figure BDA00037802753800001010
The probability distribution of the prediction classes of (a),
Figure BDA00037802753800001011
a collection of labeled exemplars representing strongly enhanced exemplars of the target domain;
b14 Constructing unknown class identification loss: consistency classification loss L for unknown class identification loss as high confidence unknown class samples unknown ：
Figure BDA00037802753800001012
Wherein the content of the first and second substances,
Figure BDA00037802753800001013
for weakly enhancing samples from the target domain
Figure BDA00037802753800001014
Screening the obtained collection of the unknown pseudo labels of the target domain,
Figure BDA00037802753800001015
representing strongly enhanced samples of a target domain
Figure BDA00037802753800001016
A predicted class probability distribution of (a);
b15 The constructed total loss function L) is:
L＝L softmax +αL ssl +βL known +γL unknown
where α, β and γ are parameters that balance the optimization objectives of the model.
Further, in an embodiment of the cross-domain remote sensing scene classification and retrieval method based on the self-supervised contrast learning provided by the present invention, the training step of the deep-domain adaptive learning network includes:
b21 C) the feature coding network f (-) can be set to three, and the source domain weakly enhanced samples and the target domain weakly enhanced samples are set
Figure BDA0003780275380000111
And target domain strongly enhanced samples
Figure BDA0003780275380000112
Respectively input into corresponding feature coding networks f (-) to respectively obtain source domain features f i s Target domain weakly enhanced image features
Figure BDA0003780275380000113
And strong enhancement of image features in the target domain
Figure BDA0003780275380000114
Wherein, the source domain weakly enhances the sample by the pair of the labeled source domain images
Figure BDA0003780275380000115
Obtaining the product by random cutting and turning;
b22 The contrast learning network g (-) can be set to two, and the target domain is weakly enhanced with the image characteristics
Figure BDA0003780275380000116
And strong enhancement of image features in the target domain
Figure BDA0003780275380000117
Respectively input into corresponding comparison learning networks g (-) to obtain the embedded characteristics of the target domain weakly enhanced images after projection in decibels
Figure BDA0003780275380000118
And strong enhancement of image embedding characteristics in the target domain
Figure BDA0003780275380000119
To calculate the contrast loss L ssl ；
B23 C (-) can be set to three and source domain features fi i s Target domain weakly enhanced image features
Figure BDA00037802753800001110
And strong enhancement of image characteristics in the target domain
Figure BDA00037802753800001111
Respectively input into corresponding classifiers c (-) to respectively obtain the source domain weakly enhanced sample class probability distribution predicted by the classifiers
Figure BDA00037802753800001112
Target domain weakly enhanced sample class probability distribution
Figure BDA00037802753800001113
Strongly enhancing sample class probability distribution with target domain
Figure BDA00037802753800001114
B24 Weakly enhancing sample class probability distribution to source domain
Figure BDA00037802753800001115
Based on the classification loss function L softmax Calculating the classification loss of the source domain;
b25 Weakly enhancing sample class probability distribution to target domain
Figure BDA00037802753800001116
Firstly, finding out the probability distribution of the target domain weakly enhanced sample class
Figure BDA00037802753800001117
Then the probability value of the category is compared with a preset predefined threshold value tau, and samples smaller than the predefined threshold value tau are abandoned so as to keep samples larger than the predefined threshold value tauDefining a sample of a threshold value tau as a pseudo label sample, and taking a class in which the maximum prediction probability is located as a known class hard label, wherein a screening formula of the sample is as follows:
Figure BDA00037802753800001118
wherein, the first and the second end of the pipe are connected with each other,
Figure BDA00037802753800001119
representing a target domain weakly enhanced sample class probability distribution
Figure BDA00037802753800001120
The category in which the maximum prediction probability that satisfies the threshold condition is located;
b26 Using target domain weakly enhanced samples
Figure BDA00037802753800001121
Known pseudo-label
Figure BDA00037802753800001122
Strongly enhanced samples as corresponding target domains
Figure BDA00037802753800001123
To calculate a target domain strong enhancement sample
Figure BDA00037802753800001124
Is known to identify the loss L known ；
B27 Selects a target domain weakly enhanced sample class probability distribution
Figure BDA0003780275380000121
And taking the sample with lower confidence level as a candidate unknown sample, wherein the specific selection formula is as follows:
Figure BDA0003780275380000122
wherein
Figure BDA0003780275380000123
For the preliminarily screened candidate unknown samples, t l Selecting a threshold value for the candidate sample, selecting a sample predicted that the probability of the unknown class is higher than the set unknown class sample selection threshold value as an unknown class sample,
Figure BDA0003780275380000124
wherein
Figure BDA0003780275380000125
As candidate samples
Figure BDA0003780275380000126
Probability of prediction as unknown class, t uk A threshold value is selected for the unknown class of samples,
Figure BDA0003780275380000127
unknown pseudo-label for target domain;
b28 With target domain unknown pseudo-tags
Figure BDA0003780275380000128
Strongly enhanced samples as target domains
Figure BDA0003780275380000129
Computing a consistent classification loss L of the unknown class sample unknown And obtaining the total loss function L and updating the parameters of the depth domain adaptive learning network.
Further, in an embodiment of the cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning provided by the invention, the step of acquiring the target domain image is as follows:
c21 Extracting a query image feature vector based on the trained feature coding network;
c22 Calculating Euclidean distances between the feature vectors of the query image and the feature vectors of each target image in the feature database one by one;
c23 According to the Euclidean distance between the target image feature vector and the query image feature vector, sorting the target image feature vectors to obtain the retrieval target corresponding to the target image feature vectors.
The construction of the input data and the training of the depth Domain adaptive learning Network are realized based on a Pythch library of a Python language, and in addition, simulation experiments of Domain adaptive methods such as ADDA (adaptive discrete Domain Adaptation), BSP (Batch singular value constraint), DAN (Deep Adaptation Network) and OSBP (Open Set Domain Adaptation) are also carried out for comparing with the cross-Domain remote sensing scene classification and retrieval method based on the self-supervision contrast learning of the invention; the invention adopts the overall classification precision and the classification confusion matrix to evaluate the classification effect, and adopts the Average Normalized Modified Retrieval Rank (ANMRR), the average retrieval precision (mAP) and PK (retrieval precision of the previous K images) to evaluate the retrieval effect, wherein the higher the average retrieval precision (mAP) and the PK values of the retrieval precision of the previous K images are, the better the retrieval performance is, the smaller the ANMRR value of the average normalized modified retrieval rank is, the better the retrieval performance is, and the comparison result is shown in table 1:
Method accuracy of classification ANMRR mAP P5 P10 P20 P50 P100
ADDA 0.602 0.2872 0.5845 0.7770 0.7540 0.7215 0.6546 0.5280
BSP 0.616 0.2800 0.5928 0.8070 0.7675 0.7238 0.6498 0.5324
DAN 0.6 0.2622 0.5997 0.7930 0.7695 0.7375 0.6658 0.5503
OSBP 0.6563 0.2725 0.5921 0.7260 0.7000 0.6880 0.6365 0.5403
The invention 0.8063 0.2222 0.6777 0.8800 0.8635 0.8318 0.7630 0.6103
TABLE 1
The results in table 1 show that the cross-domain remote sensing scene classification and retrieval method based on the self-supervision comparison learning achieves the highest retrieval accuracy, compared with the comparison method, the classification accuracy of the method is improved by 15% to 20.63%, meanwhile, the retrieval accuracy also exceeds the comparison method comprehensively, specifically, the average retrieval accuracy of the method is improved by at least 7.8% compared with the comparison method, and the P5-P100 and ANMRR of the method are superior to the comparison method. In addition, fig. 5 to 9 also show different methods and the classification confusion matrix of the present invention, in which the numerical value on the diagonal line in the classification confusion matrix represents the probability of a correct classification of a certain class, and the numerical value outside the diagonal line represents the probability of an incorrect classification of other classes, and the results show that the method of the present invention effectively improves the classification accuracy of the target domain, particularly greatly improves the classification accuracy of the unknown class of the target domain, and simultaneously reduces the confusion between the unknown class and the known class. In conclusion, the cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning provided by the invention can effectively improve the cross-domain classification and retrieval effect under the condition of data distribution difference and inconsistent class space.
According to the technical scheme, in the cross-domain remote sensing scene classification and retrieval method of the self-supervision contrast learning, input data are constructed firstly, wherein the input data comprise data of a source domain image and data of a target domain image, the data of the source domain image are labeled data, the data of the target domain image are unlabeled, the constructed input data are correspondingly enhanced, then, the enhanced data of the source domain image and the data of the target domain image are input into a corresponding feature coding network, an output result is compared with the input data, a loss function is constructed by combining a known class and an unknown class of the target domain image on the basis of the self-supervision contrast learning, so that network parameters of the feature coding network can be adjusted on the basis of the loss function, the influence of the unknown class samples existing in the target domain on the feature coding network can be reduced, and the trained depth domain adaptive learning network has a better effect when the data containing the unknown class samples are classified or retrieved.
The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited thereto. Within the scope of the technical idea of the invention, numerous simple modifications can be made to the technical solution of the invention, including combinations of the specific features in any suitable way, and the invention will not be further described in relation to the various possible combinations in order to avoid unnecessary repetition. Such simple modifications and combinations should also be considered as disclosed in the present invention, and all such modifications and combinations are intended to be included within the scope of the present invention.

Claims (10)

1. The cross-domain remote sensing scene classification and retrieval method based on the self-supervision contrast learning is characterized by comprising the following steps of:
a) Acquiring a remote sensing image, and dividing a source domain image and a target domain image of the remote sensing image to construct input data;
b) Constructing a loss function based on self-supervision contrast learning and combined with a known sample and an unknown sample of the target domain image, constructing a depth domain adaptive learning network, and training the depth domain adaptive learning network by using the input data and the loss function;
c) Classifying the target domain images by using the trained depth domain adaptive learning network, extracting target image feature vectors of the target domain images to construct a feature database, extracting query image feature vectors of the target domain query images, calculating Euclidean distances between the query image feature vectors and all the target image feature vectors in the feature database, arranging according to the Euclidean distances, and obtaining the required retrieval target according to a set Euclidean distance range.
2. The cross-domain remote sensing scene classification and retrieval method based on the self-supervision contrast learning according to claim 1, characterized in that the construction steps of the input data comprise: extracting a plurality of images {1,2,. And N } from the data set of the remote sensing image, and constructing the source domain image
Figure FDA0003780275370000011
The source domain image comprises ns marked source domain images
Figure FDA0003780275370000012
Representing annotated source domain images
Figure FDA0003780275370000013
The corresponding label, wherein,
Figure FDA0003780275370000014
representing the label space of the image with the labeling source domain, and C representing the total number of categories of the image with the labeling source domain; the target domain image is
Figure FDA0003780275370000015
The target domain image comprises nt unmarked target domain images
Figure FDA0003780275370000016
Wherein the target domain image
Figure FDA0003780275370000017
The label space of (a) is: {1,2, ·, C +1}, C +1 denotes the unknown class of the label-free target domain image.
3. The cross-domain remote sensing scene classification and retrieval method based on the self-supervision comparison learning according to claim 2, characterized in that the deep domain adaptive learning network comprises a plurality of feature coding networks f (-) and a plurality of comparison learning networks g (-) and a plurality of classifiers c (-).
4. The cross-domain remote sensing scene classification and retrieval method based on the self-supervision contrast learning according to claim 3, characterized in that the feature coding network f (-) is a depth residual network with a full connection layer removed, and an average pooling layer of the depth residual network is replaced by a bottleneck layer.
5. The cross-domain remote sensing scene classification and retrieval method based on the self-supervision comparison learning according to claim 4, characterized in that the comparison learning network g (-) is a perceptron with a ReLU activation function.
6. The cross-domain remote sensing scene classification and retrieval method based on the self-supervision contrast learning of claim 5 is characterized in that the classifier c (-) is a full-connection network, and the output dimension of the classifier c (-) is consistent with the category number of the target domain images.
7. The cross-domain remote sensing scene classification and retrieval method based on the self-supervision contrast learning according to claim 6, characterized in that the construction step of the loss function comprises:
b11 Construct source domain classification loss: and carrying out supervised learning on the source domain image, and calculating the classification accuracy by adopting cross entropy loss:
Figure FDA0003780275370000021
wherein L is softmax In order to classify the function of the loss,
Figure FDA0003780275370000022
a source domain annotated image representing the source domain image
Figure FDA0003780275370000023
True class distribution, function
Figure FDA0003780275370000024
A source domain weakly enhanced sample class probability distribution representing the classifier output,
Figure FDA0003780275370000025
a collection of labeled exemplars representing annotated images in the source domain;
b12 Construct an unsupervised contrast loss: constructing a target domain strong enhancement sample of the target domain image
Figure FDA0003780275370000026
And target domain weakly enhanced samples
Figure FDA0003780275370000027
To calculate the contrast loss L ssl ：
Figure FDA0003780275370000031
Wherein sim (-) is the similarity measure function, θ is the scaling factor, A ∈ {0,1} is an indication function for evaluating whether k equals j, B represents the number of samples selected by one training;
b13 Construct a known class identification penalty as:
Figure FDA0003780275370000032
where μ represents the proportion of samples within a training run that meet the selection requirements for a known class threshold, H (-) represents the cross entropy loss,
Figure FDA0003780275370000033
for weakly enhancing samples from the target domain
Figure FDA0003780275370000034
The collected set of the target domain known pseudo labels obtained through screening, ind represents the target domain weak enhancement sample
Figure FDA0003780275370000035
The class to which the known pseudo-label belongs after being screened, and ind ∈ {1,2.
Figure FDA0003780275370000036
Representing strongly enhanced samples of the target domain
Figure FDA0003780275370000037
Is determined based on the predicted class probability distribution of (c),
Figure FDA0003780275370000038
a collection of labeled exemplars representing strongly enhanced exemplars of the target domain;
b14 Constructing unknown class identification loss: consistency classification loss L for unknown class identification loss as high confidence unknown class samples unknown ：
Figure FDA0003780275370000039
Wherein the content of the first and second substances,
Figure FDA00037802753700000310
for weakly enhancing samples from the target domain
Figure FDA00037802753700000311
Screening the obtained collection of the unknown pseudo labels of the target domain,
Figure FDA00037802753700000312
representing strongly enhanced samples of the target domain
Figure FDA00037802753700000313
A predicted class probability distribution of (a);
b15 ) the constructed total loss function L is:
L＝L softmax +αL ssl +βL known +γL unknown
where α, β and γ are parameters that balance the optimization objectives of the model.
8. The cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning according to claim 7, characterized in that the target domain weakly-enhanced samples
Figure FDA00037802753700000314
By comparing the label-free target domain image
Figure FDA00037802753700000315
Obtaining the product by random cutting and overturning; the target domain strongly enhanced sample
Figure FDA00037802753700000316
By comparing the label-free target domain image
Figure FDA0003780275370000041
Obtaining by using a random enhancement method; the source domain weakly enhanced sample is selected from the labeled source domain image
Figure FDA0003780275370000042
And obtaining the target by random cutting and overturning.
9. The cross-domain remote sensing scene classification and retrieval method based on the self-supervision contrast learning according to claim 8, wherein the training step of the deep domain adaptive learning network comprises:
b21 The source domain weakly enhanced samples and the target domain weakly enhanced samples
Figure FDA0003780275370000043
And target domain strongly enhanced samples
Figure FDA0003780275370000044
Inputting the characteristics into the characteristic coding network f (-) to respectively obtain the source domain characteristics f i s Target domain weakly enhanced image features f j w And strong enhancement of image features in the target domain
Figure FDA00037802753700000418
B22 Weakly enhancing the target domain image features
Figure FDA00037802753700000419
And the target domain strongly enhances image features
Figure FDA00037802753700000420
Inputting the contrast learning network g (-) to obtain the embedded characteristics of the projected target domain weak enhancement image
Figure FDA0003780275370000045
And strong enhancement of image embedding characteristics in the target domain
Figure FDA0003780275370000046
To calculate the contrast loss Lssl;
b23 Characterize the source domain
Figure FDA00037802753700000417
The target domain weakly enhances image features
Figure FDA00037802753700000416
And the target domain strongly enhances image features
Figure FDA00037802753700000414
Inputting the classifier c (-) to respectively obtain the source domain weakly enhanced sample class probability distribution predicted by the classifier
Figure FDA00037802753700000412
The target domain weakly enhanced sample class probability distribution
Figure FDA00037802753700000415
And the target domain strongly enhances the sample class probability distribution
Figure FDA00037802753700000413
B24 Weakly enhancing sample class probability distribution to the source domain
Figure FDA00037802753700000411
Based on the classification loss function L softmax Calculating the classification loss of the source domain;
b25 Weakly enhancing sample class probability distribution to the target domain
Figure FDA00037802753700000410
Firstly, the category where the maximum prediction probability is located is found, the probability value of the category is compared with a preset predefined threshold value sigma, and the category which is smaller than tau is abandonedAnd (3) reserving samples larger than tau as pseudo label samples, and taking the class where the maximum prediction probability is as a known class hard label, wherein the screening formula is as follows:
Figure FDA0003780275370000047
wherein the content of the first and second substances,
Figure FDA0003780275370000048
to represent
Figure FDA0003780275370000049
A category in which the maximum prediction probability that satisfies a threshold condition is located;
b26 Using the target domain weakly enhanced samples
Figure FDA00037802753700000511
Known pseudo-label
Figure FDA00037802753700000512
Strongly enhancing samples as the corresponding target domain
Figure FDA00037802753700000510
Calculates the target domain strong enhancement samples
Figure FDA00037802753700000513
Said known class of (1) identifies a loss L known ；
B27 Selecting the target domain weakly enhanced sample class probability distribution
Figure FDA0003780275370000059
And taking the sample with lower confidence level as a candidate unknown sample, wherein the specific selection formula is as follows:
Figure FDA0003780275370000051
wherein
Figure FDA0003780275370000058
For the preliminarily screened candidate unknown samples, t l Selecting a threshold value for the candidate sample, selecting a sample predicted that the probability of the unknown class is higher than the set unknown class sample selection threshold value as an unknown class sample,
Figure FDA0003780275370000052
wherein
Figure FDA0003780275370000057
Is the candidate sample
Figure FDA0003780275370000055
Probability of prediction as unknown class, t uk A threshold value is chosen for the unknown class sample,
Figure FDA0003780275370000056
unknown pseudo-label for target domain;
b28 With the target domain unknown class pseudo-tag
Figure FDA0003780275370000053
As a strongly enhanced sample of the target domain
Figure FDA0003780275370000054
Computing a consistent classification loss L of the unknown class samples unknown And obtaining the total loss function L, and updating the parameters of the depth domain adaptive learning network by using a gradient descent algorithm.
10. The cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning according to claim 9, characterized in that the step of obtaining the retrieval target is:
c21 Extracting the query image feature vector based on the trained feature coding network;
c22 Computing Euclidean distances between the query image feature vector and each target image feature vector in the feature database one by one;
c23 According to the Euclidean distance between the target image feature vector and the query image feature vector, sorting the target image feature vectors to obtain the retrieval target corresponding to the target image feature vectors.
CN202210927707.1A 2022-08-03 2022-08-03 Cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning Pending CN115471739A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210927707.1A CN115471739A (en) 2022-08-03 2022-08-03 Cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210927707.1A CN115471739A (en) 2022-08-03 2022-08-03 Cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning

Publications (1)

Publication Number Publication Date
CN115471739A true CN115471739A (en) 2022-12-13

Family

ID=84368251

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210927707.1A Pending CN115471739A (en) 2022-08-03 2022-08-03 Cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning

Country Status (1)

Country Link
CN (1) CN115471739A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116524302A (en) * 2023-05-05 2023-08-01 广州市智慧城市投资运营有限公司 Training method, device and storage medium for scene recognition model
CN116543269A (en) * 2023-07-07 2023-08-04 江西师范大学 Cross-domain small sample fine granularity image recognition method based on self-supervision and model thereof
CN116740578A (en) * 2023-08-14 2023-09-12 北京数慧时空信息技术有限公司 Remote sensing image recommendation method based on user selection
CN117456309A (en) * 2023-12-20 2024-01-26 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) Cross-domain target identification method based on intermediate domain guidance and metric learning constraint

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116524302A (en) * 2023-05-05 2023-08-01 广州市智慧城市投资运营有限公司 Training method, device and storage medium for scene recognition model
CN116524302B (en) * 2023-05-05 2024-01-26 广州市智慧城市投资运营有限公司 Training method, device and storage medium for scene recognition model
CN116543269A (en) * 2023-07-07 2023-08-04 江西师范大学 Cross-domain small sample fine granularity image recognition method based on self-supervision and model thereof
CN116543269B (en) * 2023-07-07 2023-09-05 江西师范大学 Cross-domain small sample fine granularity image recognition method based on self-supervision and model thereof
CN116740578A (en) * 2023-08-14 2023-09-12 北京数慧时空信息技术有限公司 Remote sensing image recommendation method based on user selection
CN116740578B (en) * 2023-08-14 2023-10-27 北京数慧时空信息技术有限公司 Remote sensing image recommendation method based on user selection
CN117456309A (en) * 2023-12-20 2024-01-26 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) Cross-domain target identification method based on intermediate domain guidance and metric learning constraint
CN117456309B (en) * 2023-12-20 2024-03-15 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) Cross-domain target identification method based on intermediate domain guidance and metric learning constraint

Similar Documents

Publication Publication Date Title
CN111191732B (en) Target detection method based on full-automatic learning
CN107679250B (en) Multi-task layered image retrieval method based on deep self-coding convolutional neural network
CN113378632B (en) Pseudo-label optimization-based unsupervised domain adaptive pedestrian re-identification method
CN113190699B (en) Remote sensing image retrieval method and device based on category-level semantic hash
CN107133569B (en) Monitoring video multi-granularity labeling method based on generalized multi-label learning
CN115471739A (en) Cross-domain remote sensing scene classification and retrieval method based on self-supervision contrast learning
CN110717534B (en) Target classification and positioning method based on network supervision
CN110909820A (en) Image classification method and system based on self-supervision learning
CN108108657A (en) A kind of amendment local sensitivity Hash vehicle retrieval method based on multitask deep learning
CN109871875B (en) Building change detection method based on deep learning
CN108052966A (en) Remote sensing images scene based on convolutional neural networks automatically extracts and sorting technique
CN110852107B (en) Relation extraction method, device and storage medium
CN115934990B (en) Remote sensing image recommendation method based on content understanding
CN112132014B (en) Target re-identification method and system based on non-supervised pyramid similarity learning
CN114358188A (en) Feature extraction model processing method, feature extraction model processing device, sample retrieval method, sample retrieval device and computer equipment
CN113032613B (en) Three-dimensional model retrieval method based on interactive attention convolution neural network
CN115292532B (en) Remote sensing image domain adaptive retrieval method based on pseudo tag consistency learning
CN114897085A (en) Clustering method based on closed subgraph link prediction and computer equipment
Zhang et al. An efficient class-constrained DBSCAN approach for large-scale point cloud clustering
CN115965867A (en) Remote sensing image earth surface coverage classification method based on pseudo label and category dictionary learning
CN115393713A (en) Scene understanding method based on plot perception dynamic memory
Sari et al. Parking Lots Detection in Static Image Using Support Vector Machine Based on Genetic Algorithm.
CN114882376B (en) Convolutional neural network remote sensing image target detection method based on optimal anchor point scale
CN116932487B (en) Quantized data analysis method and system based on data paragraph division
Gaynor Unsupervised Context Distillation from Weakly Supervised Data to Augment Video Question Answering

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