WO2022077917A1 - Procédé et appareil de sélection d'échantillons de modèles de segmentation d'instances, dispositif informatique et support - Google Patents

Procédé et appareil de sélection d'échantillons de modèles de segmentation d'instances, dispositif informatique et support Download PDF

Info

Publication number
WO2022077917A1
WO2022077917A1 PCT/CN2021/096675 CN2021096675W WO2022077917A1 WO 2022077917 A1 WO2022077917 A1 WO 2022077917A1 CN 2021096675 W CN2021096675 W CN 2021096675W WO 2022077917 A1 WO2022077917 A1 WO 2022077917A1
Authority
WO
WIPO (PCT)
Prior art keywords
instance
score
sample
labeled
segmentation model
Prior art date
Application number
PCT/CN2021/096675
Other languages
English (en)
Chinese (zh)
Inventor
王俊
高鹏
Original Assignee
平安科技（深圳）有限公司
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 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2022077917A1 publication Critical patent/WO2022077917A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10081—Computed x-ray tomography [CT]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30016—Brain
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30041—Eye; Retina; Ophthalmic
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Definitions

  • the present application relates to the technical field of artificial intelligence, and can be applied to the field of image instance segmentation.
  • the present application specifically provides an instance segmentation model sample screening method, apparatus, computer equipment and medium.
  • Training datasets are datasets with rich labeling information. Collecting and labeling such datasets usually requires huge labor costs.
  • the present application can provide an instance segmentation model sample screening method, device, computer equipment and medium, which can reduce the amount of manual annotation of samples. the purpose of obtaining a large number of samples at the same time.
  • the present application discloses a sample screening method for instance segmentation model, which includes but is not limited to the following steps.
  • a plurality of first to-be-labeled samples with more information than the remaining samples are selected from the unlabeled set, and the first labeled set is obtained by manually labeling the plurality of first to-be-labeled samples. All the first samples to be labeled and all remaining samples form an unlabeled set.
  • a second to-be-labeled sample with a confidence higher than a set value is selected from all the remaining samples, and a second label set is obtained by pseudo-labeling the second to-be-labeled sample.
  • the first label set, the second label set and the already labelled set are taken together as the training set of the current instance segmentation model.
  • an instance segmentation model sample screening device which includes but is not limited to a data reading module, a first screening module, a second screening module and a data expansion module.
  • the data reading module reads the original data set, the original data set includes the unlabeled set and the labeled set.
  • the first screening module is configured to select, based on an active learning method, a plurality of first to-be-labeled samples with an amount of information greater than the remaining samples from the unlabeled set, and the plurality of first to-be-labeled samples are manually labeled as the first labeled set. All the first samples to be labeled and all remaining samples form an unlabeled set.
  • the second screening module is used to select a second to-be-labeled sample with a confidence higher than a set value from all remaining samples based on a semi-supervised learning method, and the second to-be-labeled sample is pseudo-labeled as a second label set.
  • the data expansion module uses the first label set, the second label set and the already labelled set as the training set of the current instance segmentation model.
  • the present application also provides a computer device, comprising a memory and a processor, wherein computer-readable instructions are stored in the memory, and when the computer-readable instructions are executed by the processor, the processor is made to execute any Steps of a sample screening method in an embodiment.
  • the present application also provides a storage medium storing computer-readable instructions.
  • the computer-readable instructions are executed by one or more processors, the one or more processors execute any Steps of a sample screening method in an embodiment.
  • the beneficial effects of the present application are: based on the semi-supervised active learning strategy, the present application can select the samples with the largest amount of information about the current model to be labeled by the labelers, and effectively expand the training set through the semi-supervised pseudo-labeling learning method, so the present application A large number of samples for image instance segmentation model training can be obtained while reducing the amount of manual annotation of samples, so as to achieve a more ideal instance segmentation model accuracy.
  • the present application can obtain a large number of model training samples faster while reducing manual labeling to a great extent, so that the training speed of the instance segmentation model of the present application is faster, so the present application has good practical significance and application promotion value.
  • FIG. 1 shows a schematic flowchart of a sample screening method for an instance segmentation model in some embodiments of the present application.
  • FIG. 2 shows a schematic diagram of the working principle of the sample screening apparatus for instance segmentation model in some embodiments of the present application.
  • FIG. 3 shows a schematic diagram of the working principle of the instance segmentation model in some embodiments of the present application.
  • FIG. 4 shows the scores of instance objects in some embodiments of the present application in three dimensions: category, detection frame, and segmentation contour.
  • FIG. 5 shows the scores of instance objects in other embodiments of the present application in three dimensions: category, detection frame, and segmentation contour.
  • FIG. 6 is a schematic diagram showing the comparison of instance segmentation effects that can be achieved by using the present application and the existing method on different numbers of labeled images (taking cerebral hemorrhage area segmentation and fundus edema area segmentation as examples).
  • Figure 7 is a schematic diagram showing the comparison of the model accuracy (applied to the segmentation of intracerebral hemorrhage regions) achieved using the present application and the existing method on different numbers of annotated images.
  • FIG. 8 is a schematic diagram showing the comparison of the model accuracy (applied to fundus edema region segmentation) achieved by using the present application and the existing method on different numbers of labeled images.
  • FIG. 9 shows a block diagram of the internal structure of a computer device in some embodiments of the present application.
  • this application can effectively combine Active Learning and Semi-supervised Learning. both options. Among them, this application can use the advantages of active learning to obtain the best possible generalization model by sampling as few labeled samples as possible, and use the semi-supervised learning to mine the relationship between labeled samples and unlabeled samples. Advantages of better generalizing models. The present application can combine the advantages of these two schemes, and can provide a semi-supervised active learning strategy to achieve rapid acquisition and screening of a large number of instance segmentation model samples.
  • some embodiments of the present application may provide an instance segmentation model sample screening method, which is suitable for medical image analysis with complex layouts, for example, is preferably suitable for images in which different areas are occluded from each other.
  • the method may include: But not limited to the following steps.
  • Step S1 read the original data set
  • the original data set in some embodiments of the present application may include but not limited to data sets such as unlabeled sets, labeled sets, and test sets. It should be understood that the original dataset contains relatively few labeled sets and many unlabeled sets.
  • a dataset refers to a medical image dataset
  • an unlabeled set refers to an unlabeled medical image dataset
  • a labeled set refers to a labeled medical image dataset
  • a test set refers to a medical image that can be used for model evaluation. data set.
  • Step S2 based on the active learning method, the present application first selects a plurality of first to-be-labeled samples with an amount of information greater than the remaining samples from the unlabeled set, and obtains the first labeled set by manually labeling multiple first to-be-labeled samples.
  • a label set is a partial training set formed by manual labeling. All the first to-be-labeled samples and all remaining samples form an unlabeled set in the original data set, that is, the medical image samples to be labeled and the remaining unlabeled medical image samples constitute all the Unlabeled medical image samples.
  • a new training set can be provided for the current instance segmentation model through manual annotation, the number of labeled samples that can be completed through manual annotation is limited in fact.
  • the dataset includes labeled data ⁇ (x 1 ,y 1 ),(x 2 ,y 2 ),...,(x i ,y i ) ⁇ and unlabeled data ⁇ x i+1 ,..., x n ⁇ , the first i samples in the data set are the previous labeled sets, and the remaining ni samples represent the unlabeled sets in the original data set.
  • samples with the largest amount of information may be selected from the unmarked set, and these samples are used for marking by the marking personnel.
  • the instance segmentation model formed based on the present application can work as follows: scan images (that is, images in the original data set, including unlabeled images and labeled images) through the instance segmentation model.
  • Annotated data streams and solid lines can represent annotated data streams; proposals can be generated after scanning the image, and bounding box information and mask information can be generated by classifying the proposed information, and then based on the bounding box information in the subsequent network and mask information to determine the instance detection box score (bbox_score), instance output category score (class_score) and instance contour mask score (mask_score), and then select the amount of information according to the instance detection box score, instance output category score and instance contour mask score the largest number of samples.
  • bbox_score instance output category score
  • mask_score instance contour mask score
  • the instance segmentation model of this embodiment can be extended on the basis of the Faster R-CNN model, wherein the FPN network (a feature extraction network) scans the image based on its own pyramid structure to obtain proposal information, and the process of scanning the image can be a feature map ( feature map) mapping, RPN network (a regional recommendation network) generates bounding box information and mask information by processing proposal information.
  • the processing methods can include binary classification (foreground and background classification) and BB (bounding box, detection box) ) regression, according to the bounding box information and mask information, the coordinates of the detection frame, whether there is a target in the detection frame, and the class label of the detection frame can be determined; then the bounding box information and mask information can be aligned.
  • the subsequent network in this embodiment may include a detection head (RCNN Head) and a segmentation head (Mask Head) in the instance segmentation model, and then output the above instance detection frame score and instance output category score based on the detection head, and output the above based on the segmentation head.
  • the instance contour mask score of , and the output dimension can be 1.
  • the step of selecting a plurality of first to-be-labeled samples with an amount of information greater than the remaining samples from the unlabeled set based on the active learning method in this embodiment specifically includes: Calculate the instance detection frame score, instance output category score and instance contour mask score of each sample in the unlabeled set, and then use the instance detection frame score, instance output category score and instance contour mask score to jointly determine the final score of each sample.
  • the instance detection box score is the intersection ratio (IOU) of the instance's predicted bounding box and the ground truth bounding box
  • the instance output category score is the instance's classification value
  • the instance contour mask score is the intersection ratio between the instance's predicted mask and the ground truth mask.
  • the process of determining the final score of each sample by using the instance detection frame score, the instance output category score, and the instance contour mask score includes: using the instance detection frame score, the instance output category score, and the mean and standard deviation of the instance contour mask score Calculate the score of each instance in the current sample, and then use the mean and standard deviation of the scores of each instance in the current sample to calculate the final score of the current sample. According to the negative or positive correlation between the final score and the amount of information, a plurality of first samples to be labeled are selected from the unlabeled set.
  • This embodiment can select the first sample to be labeled from the unlabeled set during the training process of the instance segmentation model, and realize manual labeling of those data based on the active learning algorithm selection. Therefore, this application can screen all unlabeled samples based on the above three-branch information metrics (instance detection frame score, instance output category score, instance outline mask score). When there are k samples, select the top k or less than k samples for manual interpretation and labeling; that is, some embodiments of the present application may perform manual interpretation and labeling on the selected unlabeled k medical image samples.
  • Some embodiments of the present application may, for example, select a plurality of first samples to be labeled from the unlabeled set according to the negative correlation between the final score and the amount of information, as shown in FIG. 4 and FIG. 5 , examples include categories, detection frames and segmentation The scores in the three dimensions of the contour, the lower the comprehensive score of these three scores, the more corresponding samples should be labeled. Select the top k or less than k samples to label for the labeling personnel.
  • relevant labeling personnel such as experts in the medical field
  • the labeled samples can be placed in the training data set directory.
  • some embodiments of the present application may further include the step of calculating a loss function.
  • the loss function of some embodiments of the present application may include five parts, namely detection frame loss L class , output class loss L bbox , outline mask loss L mask , detection frame score loss L bboxIOU , and outline mask score
  • the loss L MaskIOU a total of up to five loss functions can be used together for iterative training and learning of the instance segmentation model.
  • the loss function L semi of the semi-supervised part of the instance segmentation model is calculated as follows:
  • L semi L class +L bbox +L mask +L bboxIOU +L MaskIOU
  • the overall loss function L of the instance segmentation model is calculated as follows:
  • L sup represents the active learning part of the loss function
  • ⁇ represents the loss balance coefficient
  • the loss balance coefficient is used to suppress the potential noise caused by false annotations, and the default value is 0.01.
  • step S3 a second to-be-labeled sample with a confidence level higher than a set value is selected from all remaining samples based on a semi-supervised learning method, and a second label set is obtained by pseudo-labeling the second to-be-labeled sample.
  • a semi-supervised pseudo-annotation strategy For high-confidence samples, annotated results are automatically generated through a semi-supervised pseudo-annotation strategy.
  • the step of selecting the second to-be-labeled sample with a confidence higher than the set value from all the remaining samples based on the semi-supervised learning method includes: obtaining the instance detection frame score, instance output category score and instance outline mask of all remaining samples Score; when the instance detection frame score of the current sample is greater than the first threshold, the instance output category score is greater than the second threshold, and the instance contour mask score is greater than the third threshold, it is judged that the confidence of the current sample is higher than the set value, and the current sample is selected.
  • the sample is used as the second sample to be labeled.
  • the present application can select the second to-be-labeled samples with three metric index scores greater than 0.9 from all the remaining samples during the instance segmentation model training process, and perform pseudo-labeling to obtain approximate reference labeling results, thereby further expanding the training set. , which is conducive to better performance of the model.
  • Step S4 the first label set, the second label set and the already labelled set are taken together as the training set of the current instance segmentation model.
  • the present application can fully utilize the potential of instance segmentation. Therefore, in this application, the obtained first and second annotation sets can be added to the training set, and the model can be trained and updated, so that the information increment of the new samples obtained can greatly increase the number of medical image samples with annotations , update the training to improve the existing target instance segmentation model.
  • the present application by applying the present application to the field of intelligent aided recognition of medical images, the area delineation or quantitative evaluation of different target positions and key organ instances can be performed simultaneously, especially for image areas that may be occluded from each other, the present application can more effectively segment key target instances. . It can be seen that this application can overcome the problem of over-reliance on limited and scarce doctors and experts for labeling, and provide a large number of useful samples for the image instance segmentation model. In addition, it should be understood that the above steps of the present application may be repeatedly performed for many times.
  • some embodiments of the present disclosure are implemented by comparison on a medical image instance segmentation task.
  • the results of training after labeling by adding 500 samples step by step each time can be found that this application labels 1000-1500 samples intelligently selected.
  • the accuracy of the instance segmentation model that can only be achieved by the existing method of training 2000-3000 images can be achieved, and the labeling cost can be reduced by about 50%.
  • the present embodiment provides a graph of the segmentation results of the cerebral hemorrhage area and the fundus edema area in the actual model work. It can be seen that the results obtained in the experiments of the present application are basically consistent with the theoretical conclusions. After intelligently selecting a small number of samples, the instance segmentation effect that can only be achieved by conventional methods with more samples can be achieved. Experiments on the two tasks of CT intracerebral hemorrhage area segmentation and fundus edema area segmentation show that the application can achieve almost the same performance with only about 50% of the sample size of the conventional complete data set.
  • this application essentially provides a set of efficient human in the loop model acquisition method combining sample labeling and training, making full use of expert knowledge and high-confidence prediction of artificial intelligence, for Deep learning reduces data set requirements and provides a new implementation method, which has high practical application significance and promotion value.
  • an instance segmentation model sample screening apparatus which includes but is not limited to a data reading module, a first screening module, a second screening module, and a data expansion module.
  • the data reading module reads the original data set, the original data set includes the unlabeled set and the labeled set.
  • the first screening module is used to select a plurality of first to-be-labeled samples with an amount of information greater than the remaining samples based on an active learning method from the unlabeled set, and the plurality of first to-be-labeled samples are manually labeled as the first label set; The unlabeled sample and all remaining samples form an unlabeled set.
  • the second screening module is used to select a second to-be-labeled sample with a confidence higher than a set value from all remaining samples based on a semi-supervised learning method, and the second to-be-labeled sample is pseudo-labeled as a second label set.
  • the data expansion module uses the first label set, the second label set and the already labelled set as the training set of the current instance segmentation model.
  • the above-mentioned data such as the original data set and the training set may also be stored in a node of a blockchain.
  • this application selects some high-value samples from a large number of unlabeled original medical images and labels them for labelers (such as doctors), and does not need to label all samples.
  • labelers such as doctors
  • This application can select the samples with the largest amount of information to speed up the training of the instance segmentation model, and the amount of manually labeled data is significantly reduced, which provides a new implementation method for deep learning to reduce data set requirements, realizes efficient data and computing resource utilization, and saves computing. LF.
  • the present application also provides a computer device, including a memory and a processor, wherein computer-readable instructions are stored in the memory, and when the computer-readable instructions are executed by the processor, the processor executes any The steps of the sample screening method in the Examples.
  • the computer equipment can be a PC, a portable electronic device such as a PAD, a tablet computer, a laptop computer, or an intelligent mobile terminal such as a mobile phone, which is not limited to the description here; the computer equipment can also be implemented by a server, The server can be constituted by a cluster system, and in order to realize the function of each unit, it is merged into one computer device or a separate set of functions of each unit.
  • Step S1 reading the original data set, the original data set in this application may include unlabeled sets and labeled sets.
  • Step S2 based on the active learning method, select a plurality of first to-be-labeled samples with an amount of information greater than the remaining samples from the unlabeled set, and obtain a first labeled set by manually labeling a plurality of first to-be-labeled samples; all the first to be labeled samples are obtained. The sample and all remaining samples form the unlabeled set.
  • the step of selecting a plurality of first to-be-labeled samples with more information than the remaining samples from the unlabeled set based on the active learning method includes: calculating the instance detection frame score, instance output category score and instance outline mask of each sample in the unlabeled set score, to determine the final score of each sample by using the instance detection frame score, the instance output category score and the instance outline mask score; specifically, in some embodiments of the present application, the instance detection frame score is the intersection of the instance detection frame and the real frame In the comparison, the instance output category score is the classification value of the instance, and the instance contour mask score is the intersection ratio between the detection mask of the instance and the real mask.
  • the process of using the instance detection frame score, instance output category score and instance contour mask score to determine the final score of each sample includes: calculating the current sample using the mean and standard deviation of the instance detection frame score, instance output category score and instance contour mask score The score of each instance in the current sample; the final score of the current sample is calculated using the mean and standard deviation of the scores of each instance in the current sample. According to the negative or positive correlation between the final score and the amount of information, a plurality of first samples to be labeled are selected from the unlabeled set. The first to-be-labeled sample can be selected from the unlabeled set during instance segmentation model training.
  • step S3 a second to-be-labeled sample with a confidence level higher than a set value is selected from all remaining samples based on a semi-supervised learning method, and a second label set is obtained by pseudo-labeling the second to-be-labeled sample.
  • the step of selecting the second to-be-labeled sample with a confidence higher than the set value from all the remaining samples based on the semi-supervised learning method includes: obtaining the instance detection frame score, instance output category score and instance outline mask of all remaining samples Score; when the instance detection frame score of the current sample is greater than the first threshold, the instance output category score is greater than the second threshold, and the instance contour mask score is greater than the third threshold, it is judged that the confidence of the current sample is higher than the set value, and the current sample is selected.
  • the sample is used as the second sample to be labeled.
  • the present application can select the second to-be-labeled sample from all remaining samples during the instance segmentation model training process. Step S4, the first label set, the second label set and the already labelled set are taken together as the training set of the current instance segmentation model.
  • a storage medium storing computer-readable instructions, when executed by one or more processors, causes the one or more processors to perform the steps of the sample screening method as follows in any embodiment of the present application.
  • Step S1 reading the original data set, the original data set in this application may include unlabeled sets and labeled sets.
  • Step S2 based on the active learning method, select a plurality of first to-be-labeled samples with an amount of information greater than the remaining samples from the unlabeled set, and obtain a first labeled set by manually labeling a plurality of first to-be-labeled samples; all the first to be labeled samples are obtained. The sample and all remaining samples form the unlabeled set.
  • the step of selecting a plurality of first to-be-labeled samples with more information than the remaining samples from the unlabeled set based on the active learning method includes: calculating the instance detection frame score, instance output category score and instance outline mask of each sample in the unlabeled set score, to determine the final score of each sample by using the instance detection frame score, the instance output category score and the instance outline mask score; specifically, in some embodiments of the present application, the instance detection frame score is the intersection of the instance detection frame and the real frame In the comparison, the instance output category score is the classification value of the instance, and the instance contour mask score is the intersection ratio between the detection mask of the instance and the real mask.
  • the process of using the instance detection frame score, instance output category score and instance contour mask score to determine the final score of each sample includes: calculating the current sample using the mean and standard deviation of the instance detection frame score, instance output category score and instance contour mask score The score of each instance in the current sample; the final score of the current sample is calculated using the mean and standard deviation of the scores of each instance in the current sample. According to the negative or positive correlation between the final score and the amount of information, a plurality of first samples to be labeled are selected from the unlabeled set. The first to-be-labeled sample can be selected from the unlabeled set during instance segmentation model training.
  • step S3 a second to-be-labeled sample with a confidence higher than the set value is selected from all remaining samples based on a semi-supervised learning method, and a second label set is obtained by pseudo-labeling the second to-be-labeled sample.
  • the step of selecting the second to-be-labeled sample with a confidence higher than the set value from all the remaining samples based on the semi-supervised learning method includes: obtaining the instance detection frame score, instance output category score and instance outline mask of all remaining samples Score; when the instance detection frame score of the current sample is greater than the first threshold, the instance output category score is greater than the second threshold, and the instance contour mask score is greater than the third threshold, it is judged that the confidence of the current sample is higher than the set value, and the current sample is selected.
  • the sample is used as the second sample to be labeled.
  • the present application can select the second to-be-labeled sample from all remaining samples during the instance segmentation model training process. Step S4, the first label set, the second label set and the already labelled set are taken together as the training set of the current instance segmentation model.
  • the blockchain referred to in this application is a new application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm.
  • Blockchain essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information to verify its Validity of information (anti-counterfeiting) and generation of the next block.
  • the blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.
  • Logic and/or steps represented in flowcharts or otherwise described herein, for example, may be considered an ordered listing of executable instructions for implementing the logical functions, and may be embodied in any computer-readable storage medium , for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device), or in conjunction with these instruction execution systems, device or equipment.
  • a "computer-readable storage medium” can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or apparatus .
  • the computer-readable storage medium may be non-volatile or volatile.
  • Computer readable storage media include the following: electrical connections with one or more wiring (electronic devices), portable computer disk cartridges (magnetic devices), random access memory (RAM, Random Access Memory), Read-Only Memory (ROM, Read-Only Memory), Erasable and Editable Read-Only Memory (EPROM, Erasable Programmable Read-Only Memory, or Flash Memory), Optical Devices, and Portable Optical Disc Read-Only Memory (CDROM, Compact Disc Read-Only Memory).
  • wiring electronic devices
  • portable computer disk cartridges magnetic devices
  • RAM Random Access Memory
  • ROM Read-Only Memory
  • EPROM Erasable Programmable Read-Only Memory
  • Optical Devices and Portable Optical Disc Read-Only Memory (CDROM, Compact Disc Read-Only Memory).
  • the computer-readable storage medium may even be paper or other suitable medium on which the program can be printed, as the paper or other medium may be optically scanned, for example, and then edited, interpreted or, if necessary, otherwise Process in a suitable manner to obtain the program electronically and then store it in computer memory.
  • first and second are only used for descriptive purposes, and should not be construed as indicating or implying relative importance or implying the number of indicated technical features. Thus, a feature delimited with “first”, “second” may expressly or implicitly include at least one of that feature.
  • plurality means at least two, such as two, three, etc., unless expressly and specifically defined otherwise.

Abstract

La présente invention concerne un procédé de sélection d'échantillons de modèles de segmentation d'instances, qui se rapporte à l'intelligence artificielle, et peut être utilisé pour un scénario d'aide à l'analyse d'images médicales. Le procédé consiste à : lire un ensemble de données initiales ; prélever, sur la base d'un mode d'apprentissage actif et à partir d'un ensemble non marqué, des premiers échantillons à marquer, dont les quantités d'informations sont supérieures à celles des échantillons restants, de sorte à obtenir un premier ensemble marqué d'une manière à marquer manuellement la pluralité de premiers échantillons à marquer ; sélectionner, sur la base d'un mode d'apprentissage semi-supervisé et de l'ensemble des échantillons restants, des seconds échantillons à marquer, dont les coefficients de confiance sont supérieurs à une valeur définie, de sorte à obtenir un second ensemble marqué d'une manière à pseudo-marquer lesdits seconds échantillons ; et définir le premier ensemble marqué, le second ensemble marqué et un ensemble marqué conjointement en tant qu'ensemble d'apprentissage. Au moyen du procédé, une quantité de marquage manuel d'échantillons est réduite, et un grand nombre d'échantillons utilisés pour l'apprentissage d'un modèle de segmentation d'instances d'images peuvent être obtenus, de sorte à pouvoir obtenir une précision plus optimale pour le modèle de segmentation d'instances. De plus, le procédé se rapporte en outre à une technologie de chaîne de blocs, et à la fois un ensemble de données initiales et un ensemble d'apprentissage peuvent être stockées dans une chaîne de blocs.
PCT/CN2021/096675 2020-10-14 2021-05-28 Procédé et appareil de sélection d'échantillons de modèles de segmentation d'instances, dispositif informatique et support WO2022077917A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011099366.0A CN112163634B (zh) 2020-10-14 2020-10-14 实例分割模型样本筛选方法、装置、计算机设备及介质
CN202011099366.0 2020-10-14

Publications (1)

Publication Number Publication Date
WO2022077917A1 true WO2022077917A1 (fr) 2022-04-21

Family

ID=73866927

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/096675 WO2022077917A1 (fr) 2020-10-14 2021-05-28 Procédé et appareil de sélection d'échantillons de modèles de segmentation d'instances, dispositif informatique et support

Country Status (2)

Country Link
CN (1) CN112163634B (fr)
WO (1) WO2022077917A1 (fr)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115482436A (zh) * 2022-09-21 2022-12-16 北京百度网讯科技有限公司 图像筛选模型的训练方法、装置以及图像筛选方法
CN116229369A (zh) * 2023-03-03 2023-06-06 嘉洋智慧安全科技(北京)股份有限公司 人流量的检测方法、装置、设备及计算机可读存储介质
CN117218132A (zh) * 2023-11-09 2023-12-12 铸新科技(苏州)有限责任公司 一种整体炉管寿命分析方法、装置、计算机设备及介质
CN117315263A (zh) * 2023-11-28 2023-12-29 杭州申昊科技股份有限公司 一种目标轮廓分割装置、训练方法、分割方法、电子设备

Families Citing this family (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112163634B (zh) * 2020-10-14 2023-09-05 平安科技（深圳）有限公司 实例分割模型样本筛选方法、装置、计算机设备及介质
CN112381834B (zh) * 2021-01-08 2022-06-03 之江实验室 一种对图像交互式实例分割的标注方法
CN112884055B (zh) * 2021-03-03 2023-02-03 歌尔股份有限公司 一种目标标注方法和一种目标标注装置
CN112884060B (zh) * 2021-03-09 2024-04-26 联仁健康医疗大数据科技股份有限公司 图像标注方法、装置、电子设备及存储介质
CN113487738B (zh) * 2021-06-24 2022-07-05 哈尔滨工程大学 基于虚拟知识迁移的建筑物及其遮挡区域单体化提取方法
CN113255669B (zh) * 2021-06-28 2021-10-01 山东大学 任意形状自然场景文本检测方法及系统
CN113673505A (zh) * 2021-06-29 2021-11-19 北京旷视科技有限公司 实例分割模型的训练方法、装置、系统及存储介质
CN113361535B (zh) * 2021-06-30 2023-08-01 北京百度网讯科技有限公司 图像分割模型训练、图像分割方法及相关装置
CN113554068B (zh) * 2021-07-05 2023-10-31 华侨大学 一种实例分割数据集的半自动标注方法、装置及可读介质
CN113487617A (zh) * 2021-07-26 2021-10-08 推想医疗科技股份有限公司 数据处理方法、装置、电子设备以及存储介质
CN113593531B (zh) * 2021-07-30 2024-05-03 思必驰科技股份有限公司 语音识别模型训练方法及系统
CN113705687B (zh) * 2021-08-30 2023-03-24 平安科技（深圳）有限公司 基于人工智能的图像实例标注方法及相关设备
CN113762286A (zh) * 2021-09-16 2021-12-07 平安国际智慧城市科技股份有限公司 数据模型训练方法、装置、设备及介质
CN114612702A (zh) * 2022-01-24 2022-06-10 珠高智能科技(深圳)有限公司 基于深度学习的图像数据标注系统及其方法
CN114462531A (zh) * 2022-01-30 2022-05-10 支付宝(杭州)信息技术有限公司 一种模型训练方法、装置及电子设备
CN114359676B (zh) * 2022-03-08 2022-07-19 人民中科(济南)智能技术有限公司 训练目标检测模型和构建样本集的方法、装置及存储介质
CN115439686B (zh) * 2022-08-30 2024-01-09 一选(浙江)医疗科技有限公司 一种基于扫描影像的关注对象检测方法及系统
CN115170809B (zh) * 2022-09-06 2023-01-03 浙江大华技术股份有限公司 图像分割模型训练、图像分割方法、装置、设备及介质
CN115393361B (zh) * 2022-10-28 2023-02-03 湖南大学 低标注成本的皮肤病图像分割方法、装置、设备及介质
CN117115568B (zh) * 2023-10-24 2024-01-16 浙江啄云智能科技有限公司 数据筛选方法、装置、设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101853400A (zh) * 2010-05-20 2010-10-06 武汉大学 基于主动学习和半监督学习的多类图像分类方法
CN103150578A (zh) * 2013-04-09 2013-06-12 山东师范大学 一种基于半监督学习的支持向量机分类器训练方法
CN108985334A (zh) * 2018-06-15 2018-12-11 广州深域信息科技有限公司 基于自监督过程改进主动学习的通用物体检测系统及方法
CN111401293A (zh) * 2020-03-25 2020-07-10 东华大学 一种基于Head轻量化Mask Scoring R-CNN的手势识别方法
CN112163634A (zh) * 2020-10-14 2021-01-01 平安科技（深圳）有限公司 实例分割模型样本筛选方法、装置、计算机设备及介质

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130097103A1 (en) * 2011-10-14 2013-04-18 International Business Machines Corporation Techniques for Generating Balanced and Class-Independent Training Data From Unlabeled Data Set
CN109447169B (zh) * 2018-11-02 2020-10-27 北京旷视科技有限公司 图像处理方法及其模型的训练方法、装置和电子系统
CN109949317B (zh) * 2019-03-06 2020-12-11 东南大学 基于逐步对抗学习的半监督图像实例分割方法
US10430946B1 (en) * 2019-03-14 2019-10-01 Inception Institute of Artificial Intelligence, Ltd. Medical image segmentation and severity grading using neural network architectures with semi-supervised learning techniques
CN111666993A (zh) * 2020-05-28 2020-09-15 平安科技（深圳）有限公司 医学图像样本筛查方法、装置、计算机设备和存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101853400A (zh) * 2010-05-20 2010-10-06 武汉大学 基于主动学习和半监督学习的多类图像分类方法
CN103150578A (zh) * 2013-04-09 2013-06-12 山东师范大学 一种基于半监督学习的支持向量机分类器训练方法
CN108985334A (zh) * 2018-06-15 2018-12-11 广州深域信息科技有限公司 基于自监督过程改进主动学习的通用物体检测系统及方法
CN111401293A (zh) * 2020-03-25 2020-07-10 东华大学 一种基于Head轻量化Mask Scoring R-CNN的手势识别方法
CN112163634A (zh) * 2020-10-14 2021-01-01 平安科技（深圳）有限公司 实例分割模型样本筛选方法、装置、计算机设备及介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
CHEN RONG BVSB, SAR , RONG CHEN, YONG-FENG CAO, HONG SUN: "Multi-class Image Classification with Active Learning and Semi-supervised Learning", ACTA AUTOMATICA SINICA, KEXUE CHUBANSHE, BEIJING, CN, vol. 37863, no. 1, 31 August 2011 (2011-08-31), CN , XP055921885, ISSN: 0254-4156, DOI: 10.3724/SP.J.1004.2011.00954 *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115482436A (zh) * 2022-09-21 2022-12-16 北京百度网讯科技有限公司 图像筛选模型的训练方法、装置以及图像筛选方法
CN115482436B (zh) * 2022-09-21 2023-06-30 北京百度网讯科技有限公司 图像筛选模型的训练方法、装置以及图像筛选方法
CN116229369A (zh) * 2023-03-03 2023-06-06 嘉洋智慧安全科技(北京)股份有限公司 人流量的检测方法、装置、设备及计算机可读存储介质
CN117218132A (zh) * 2023-11-09 2023-12-12 铸新科技(苏州)有限责任公司 一种整体炉管寿命分析方法、装置、计算机设备及介质
CN117218132B (zh) * 2023-11-09 2024-01-19 铸新科技(苏州)有限责任公司 一种整体炉管寿命分析方法、装置、计算机设备及介质
CN117315263A (zh) * 2023-11-28 2023-12-29 杭州申昊科技股份有限公司 一种目标轮廓分割装置、训练方法、分割方法、电子设备
CN117315263B (zh) * 2023-11-28 2024-03-22 杭州申昊科技股份有限公司 一种目标轮廓装置、训练方法、分割方法、电子设备及存储介质

Also Published As

Publication number Publication date
CN112163634B (zh) 2023-09-05
CN112163634A (zh) 2021-01-01

Similar Documents

Publication Publication Date Title
WO2022077917A1 (fr) Procédé et appareil de sélection d'échantillons de modèles de segmentation d'instances, dispositif informatique et support
JP6843086B2 (ja) 画像処理システム、画像においてマルチラベル意味エッジ検出を行う方法、および、非一時的コンピューター可読記憶媒体
Kisilev et al. Medical image description using multi-task-loss CNN
CN110428432B (zh) 结肠腺体图像自动分割的深度神经网络算法
Xiao et al. A weakly supervised semantic segmentation network by aggregating seed cues: the multi-object proposal generation perspective
WO2022001623A1 (fr) Procédé et appareil de traitement d'image faisant appel à l'intelligence artificielle, dispositif et support de stockage
CN111931931B (zh) 一种针对病理全场图像的深度神经网络训练方法、装置
US10789712B2 (en) Method and system for image analysis to detect cancer
WO2021189913A1 (fr) Procédé et appareil de segmentation d'objet cible dans une image, et dispositif électronique et support d'enregistrement
US11875512B2 (en) Attributionally robust training for weakly supervised localization and segmentation
Huang et al. Omni-supervised learning: scaling up to large unlabelled medical datasets
CN111882560A (zh) 一种基于加权全卷积神经网络的肺实质ct图像分割方法
CN110472049B (zh) 疾病筛查文本分类方法、计算机设备和可读存储介质
CN108154191B (zh) 文档图像的识别方法和系统
WO2022089257A1 (fr) Procédé de traitement d'image médicale, appareil, dispositif, support de stockage informatique et produit
WO2021057148A1 (fr) Procédé et dispositif de stratification de tissu cérébral basés sur un réseau neuronal et dispositif informatique
CN110889437B (zh) 一种图像处理方法、装置、电子设备及存储介质
CN110533046A (zh) 一种图像实例分割方法和装置
CN113987119A (zh) 一种数据检索方法、跨模态数据匹配模型处理方法和装置
Zhang et al. An efficient semi-supervised manifold embedding for crowd counting
CN116525075A (zh) 基于少样本学习的甲状腺结节计算机辅助诊断方法及系统
Fu et al. Medical image retrieval and classification based on morphological shape feature
Ullah et al. DSFMA: Deeply supervised fully convolutional neural networks based on multi-level aggregation for saliency detection
WO2023029348A1 (fr) Procédé d'étiquetage d'instance d'image basé sur l'intelligence artificielle, et dispositif associé
Wu et al. Automatic mass detection from mammograms with region-based convolutional neural network

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21878971

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21878971

Country of ref document: EP

Kind code of ref document: A1