WO2022037233A9 - Small sample visual target identification method based on self-supervised knowledge transfer - Google Patents

Small sample visual target identification method based on self-supervised knowledge transfer Download PDF

Info

Publication number
WO2022037233A9
WO2022037233A9 PCT/CN2021/101128 CN2021101128W WO2022037233A9 WO 2022037233 A9 WO2022037233 A9 WO 2022037233A9 CN 2021101128 W CN2021101128 W CN 2021101128W WO 2022037233 A9 WO2022037233 A9 WO 2022037233A9
Authority
WO
WIPO (PCT)
Prior art keywords
data
feature
self
space
method based
Prior art date
Application number
PCT/CN2021/101128
Other languages
French (fr)
Chinese (zh)
Other versions
WO2022037233A1 (en
Inventor
宋杰
宋明黎
冯尊磊
陈刚
Original Assignee
浙江大学
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 浙江大学 filed Critical 浙江大学
Publication of WO2022037233A1 publication Critical patent/WO2022037233A1/en
Publication of WO2022037233A9 publication Critical patent/WO2022037233A9/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • 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
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • 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

Landscapes

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

Abstract

A small sample visual target identification method based on self-supervised knowledge transfer. The method comprises: 1) collecting unlabeled auxiliary data which is weakly related to a task and has a relatively large amount of data, and labeled target data which is strongly related to the task and has a relatively small amount of data; 2) constructing, on the unlabeled auxiliary data with a relatively large amount of data and by means of data conversion, a positive sample pair and a negative sample pair, and performing self-supervised learning by using a contrast loss function, so as to pre-train a deep neural network; 3) extracting a feature of target data by using a pre-trained model, and performing data dimension reduction on the basis of a feature space, so as to learn of a feature sub-space with a relatively strong discriminative ability regarding the target data; and 4) using a feature expression, in the sub-space, of a small amount of labeled data of each category as a feature prototype of the category, and performing classification prediction on test data by using a nearest neighbor method.
PCT/CN2021/101128 2020-08-18 2021-06-21 Small sample visual target identification method based on self-supervised knowledge transfer WO2022037233A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010830474.4 2020-08-18
CN202010830474.4A CN112069921A (en) 2020-08-18 2020-08-18 Small sample visual target identification method based on self-supervision knowledge migration

Publications (2)

Publication Number Publication Date
WO2022037233A1 WO2022037233A1 (en) 2022-02-24
WO2022037233A9 true WO2022037233A9 (en) 2022-04-21

Family

ID=73661981

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/101128 WO2022037233A1 (en) 2020-08-18 2021-06-21 Small sample visual target identification method based on self-supervised knowledge transfer

Country Status (2)

Country Link
CN (1) CN112069921A (en)
WO (1) WO2022037233A1 (en)

Families Citing this family (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112069921A (en) * 2020-08-18 2020-12-11 浙江大学 Small sample visual target identification method based on self-supervision knowledge migration
CN113298150A (en) * 2021-05-25 2021-08-24 东北林业大学 Small sample plant disease identification method based on transfer learning and self-learning
CN113314205B (en) * 2021-05-28 2022-05-17 北京航空航天大学 Efficient medical image labeling and learning system
CN113313684B (en) * 2021-05-28 2022-11-25 北京航空航天大学 Video-based industrial defect detection system under dim light condition
CN113781404B (en) * 2021-08-19 2023-12-01 浙江大学 Road disease detection method and system based on self-supervision pre-training
CN113688757A (en) * 2021-08-30 2021-11-23 五邑大学 SAR image recognition method and device and storage medium
CN114596844A (en) * 2022-03-18 2022-06-07 腾讯科技（深圳）有限公司 Acoustic model training method, voice recognition method and related equipment
CN114494890B (en) * 2022-04-14 2022-08-23 广州市玄武无线科技股份有限公司 Model training method, commodity image management method and device
CN114841257B (en) * 2022-04-21 2023-09-22 北京交通大学 Small sample target detection method based on self-supervision comparison constraint
CN114596312B (en) * 2022-05-07 2022-08-02 中国科学院深圳先进技术研究院 Video processing method and device
CN115131613B (en) * 2022-07-01 2024-04-02 中国科学技术大学 Small sample image classification method based on multidirectional knowledge migration
CN114936615B (en) * 2022-07-25 2022-10-14 南京大数据集团有限公司 Small sample log information anomaly detection method based on characterization consistency correction
CN115100532B (en) * 2022-08-02 2023-04-07 北京卫星信息工程研究所 Small sample remote sensing image target detection method and system
CN115080749B (en) * 2022-08-16 2022-11-08 之江实验室 Weak supervision text classification method, system and device based on self-supervision training
CN115641483A (en) * 2022-09-16 2023-01-24 北京大学 Unsupervised low-illumination-area self-adaptive training method and detection method
CN115410059B (en) * 2022-11-01 2023-03-24 山东锋士信息技术有限公司 Remote sensing image part supervision change detection method and device based on contrast loss
CN115879004A (en) * 2022-12-21 2023-03-31 北京百度网讯科技有限公司 Target model training method, apparatus, electronic device, medium, and program product
CN115861720B (en) * 2023-02-28 2023-06-30 人工智能与数字经济广东省实验室(广州) Small sample subclass image classification and identification method

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180174042A1 (en) * 2016-12-20 2018-06-21 Intel Corporation Supervised training and pattern matching techniques for neural networks
CN108985334B (en) * 2018-06-15 2022-04-12 拓元(广州)智慧科技有限公司 General object detection system and method for improving active learning based on self-supervision process
US20200160177A1 (en) * 2018-11-16 2020-05-21 Royal Bank Of Canada System and method for a convolutional neural network for multi-label classification with partial annotations
CN110363231B (en) * 2019-06-27 2023-01-06 平安科技（深圳）有限公司 Abnormity identification method and device based on semi-supervised deep learning and storage medium
CN110414600A (en) * 2019-07-27 2019-11-05 西安电子科技大学 A kind of extraterrestrial target small sample recognition methods based on transfer learning
CN111259720B (en) * 2019-10-30 2023-05-26 北京中科研究院 Unsupervised pedestrian re-identification method based on self-supervision agent feature learning
CN111191732B (en) * 2020-01-03 2021-05-14 天津大学 Target detection method based on full-automatic learning
CN111222471B (en) * 2020-01-09 2022-07-15 中国科学技术大学 Zero sample training and related classification method based on self-supervision domain perception network
CN112069921A (en) * 2020-08-18 2020-12-11 浙江大学 Small sample visual target identification method based on self-supervision knowledge migration

Also Published As

Publication number Publication date
CN112069921A (en) 2020-12-11
WO2022037233A1 (en) 2022-02-24

Similar Documents

Publication Publication Date Title
WO2022037233A9 (en) Small sample visual target identification method based on self-supervised knowledge transfer
Tang et al. Intelligent fault diagnosis of hydraulic piston pump based on deep learning and Bayesian optimization
Zhang et al. Fault diagnosis of planetary gearbox using a novel semi-supervised method of multiple association layers networks
CN103942568B (en) A kind of sorting technique based on unsupervised feature selection
CN106156003A (en) A kind of question sentence understanding method in question answering system
CN114004252A (en) Bearing fault diagnosis method, device and equipment
CN107423284A (en) Merge the construction method and system of the sentence expression of Chinese language words internal structural information
CN103942749B (en) A kind of based on revising cluster hypothesis and the EO-1 hyperion terrain classification method of semi-supervised very fast learning machine
CN112990296A (en) Image-text matching model compression and acceleration method and system based on orthogonal similarity distillation
Yao et al. Multiscale domain adaption models and their application in fault transfer diagnosis of planetary gearboxes
Ragib et al. Pakhichini: Automatic bird species identification using deep learning
CN116152554A (en) Knowledge-guided small sample image recognition system
CN108805155A (en) Learn the semisupervised classification method of incidence matrix and Laplace regularization least square simultaneously
CN109190471B (en) Attention model method for video monitoring pedestrian search based on natural language description
CN102063628A (en) Method for extracting double-sided braille
Sreenivasulu et al. Implementation of latest machine learning approaches for students grade prediction
CN113011196A (en) Concept-enhanced representation and one-way attention-containing subjective question automatic scoring neural network model
Rethik et al. Attention Based Mapping for Plants Leaf to Classify Diseases using Vision Transformer
CN107909090A (en) Learn semi-supervised music-book on pianoforte difficulty recognition methods based on estimating
CN104050451A (en) Robust target tracking method based on multi-channel Haar-like characteristics
CN113959719B (en) SOT-SVM-based variable-working-condition rolling bearing fault diagnosis method
CN110298331A (en) A kind of testimony of a witness comparison method
CN114036947B (en) Small sample text classification method and system for semi-supervised learning
CN113139464B (en) Power grid fault detection method
Tomar et al. A Comparative Analysis of Activation Function, Evaluating their Accuracy and Efficiency when Applied to Miscellaneous Datasets

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: 21857330

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: 21857330

Country of ref document: EP

Kind code of ref document: A1