CN112884022B - 一种基于图像平移的无监督深度表征学习方法及系统 - Google Patents
一种基于图像平移的无监督深度表征学习方法及系统 Download PDFInfo
- Publication number
- CN112884022B CN112884022B CN202110128485.2A CN202110128485A CN112884022B CN 112884022 B CN112884022 B CN 112884022B CN 202110128485 A CN202110128485 A CN 202110128485A CN 112884022 B CN112884022 B CN 112884022B
- Authority
- CN
- China
- Prior art keywords
- image
- translation
- mask
- neural network
- transformation
- 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.)
- Active
Links
- 238000013519 translation Methods 0.000 title claims abstract description 151
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000012512 characterization method Methods 0.000 title claims abstract description 36
- 230000009466 transformation Effects 0.000 claims abstract description 84
- 238000013528 artificial neural network Methods 0.000 claims abstract description 66
- 230000006870 function Effects 0.000 claims abstract description 50
- 238000000605 extraction Methods 0.000 claims abstract description 11
- 230000008569 process Effects 0.000 claims abstract description 11
- 238000006243 chemical reaction Methods 0.000 claims abstract description 9
- 239000011159 matrix material Substances 0.000 claims description 25
- 238000012549 training Methods 0.000 claims description 21
- 238000013507 mapping Methods 0.000 claims description 7
- 230000001537 neural effect Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 12
- 238000000844 transformation Methods 0.000 description 11
- 238000012360 testing method Methods 0.000 description 6
- 238000007477 logistic regression Methods 0.000 description 5
- 238000011176 pooling Methods 0.000 description 4
- 208000037170 Delayed Emergence from Anesthesia Diseases 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000010365 information processing Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000000873 masking effect Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000004091 panning Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000007786 learning performance Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000004205 output neuron Anatomy 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/70—Labelling scene content, e.g. deriving syntactic or semantic representations
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
Description
总样本数 | 训练集 | 测试集 | 类别数 | 图像尺寸 | |
CIFAR10 | 6w | 5w | 1w | 10 | 32×32 |
CIFAR100 | 6w | 5w | 1w | 100 | 32×32 |
STL10 | 11.3w | 10w/5000 | 8000 | 10 | 96×96 |
Flower | 1360 | 1020 | 340 | 17 | 96×96 |
数据集 | 预测图像旋转 | 预测几何变换 | 本方案 |
CIFAR10 | 73.0 | 75.5 | 78.7 |
CIFAR100 | 39.1 | 43.7 | 45.2 |
STL10 | 71.0 | 73.3 | 78.4 |
Flower | 51.5 | 51.5 | 61.2 |
Claims (8)
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110128485.2A CN112884022B (zh) | 2021-01-29 | 2021-01-29 | 一种基于图像平移的无监督深度表征学习方法及系统 |
US18/274,217 US20240104885A1 (en) | 2021-01-29 | 2021-11-24 | Method and system for unsupervised deep representation learning based on image translation |
PCT/CN2021/132631 WO2022160898A1 (zh) | 2021-01-29 | 2021-11-24 | 一种基于图像平移的无监督深度表征学习方法及系统 |
ZA2023/08288A ZA202308288B (en) | 2021-01-29 | 2023-08-28 | Method and system for unsupervised deep representation learning based on image translation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110128485.2A CN112884022B (zh) | 2021-01-29 | 2021-01-29 | 一种基于图像平移的无监督深度表征学习方法及系统 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112884022A CN112884022A (zh) | 2021-06-01 |
CN112884022B true CN112884022B (zh) | 2021-11-12 |
Family
ID=76051996
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110128485.2A Active CN112884022B (zh) | 2021-01-29 | 2021-01-29 | 一种基于图像平移的无监督深度表征学习方法及系统 |
Country Status (4)
Country | Link |
---|---|
US (1) | US20240104885A1 (zh) |
CN (1) | CN112884022B (zh) |
WO (1) | WO2022160898A1 (zh) |
ZA (1) | ZA202308288B (zh) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112884022B (zh) * | 2021-01-29 | 2021-11-12 | 浙江师范大学 | 一种基于图像平移的无监督深度表征学习方法及系统 |
Family Cites Families (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10726560B2 (en) * | 2014-10-31 | 2020-07-28 | Fyusion, Inc. | Real-time mobile device capture and generation of art-styled AR/VR content |
WO2018057714A1 (en) * | 2016-09-21 | 2018-03-29 | The General Hospital Corporation | Systems, methods and media for automatically generating a bone age assessment from a radiograph |
CN109903396B (zh) * | 2019-03-20 | 2022-12-16 | 洛阳中科信息产业研究院 | 一种基于曲面参数化的牙齿三维模型自动分割方法 |
CN110136136B (zh) * | 2019-05-27 | 2022-02-08 | 北京达佳互联信息技术有限公司 | 场景分割方法、装置、计算机设备及存储介质 |
CN111091575B (zh) * | 2019-12-31 | 2022-10-18 | 电子科技大学 | 一种基于强化学习方法的医学图像分割方法 |
CN111369540B (zh) * | 2020-03-06 | 2023-06-02 | 西安电子科技大学 | 基于掩码卷积神经网络的植物叶片病害识别方法 |
CN111489323B (zh) * | 2020-04-09 | 2023-09-19 | 中国科学技术大学先进技术研究院 | 双光场图像融合方法、装置、设备及可读存储介质 |
CN111783986B (zh) * | 2020-07-02 | 2024-06-14 | 清华大学 | 网络训练方法及装置、姿态预测方法及装置 |
CN112258436A (zh) * | 2020-10-21 | 2021-01-22 | 华为技术有限公司 | 图像处理模型的训练方法、装置、图像处理方法及模型 |
CN112884022B (zh) * | 2021-01-29 | 2021-11-12 | 浙江师范大学 | 一种基于图像平移的无监督深度表征学习方法及系统 |
-
2021
- 2021-01-29 CN CN202110128485.2A patent/CN112884022B/zh active Active
- 2021-11-24 US US18/274,217 patent/US20240104885A1/en active Pending
- 2021-11-24 WO PCT/CN2021/132631 patent/WO2022160898A1/zh active Application Filing
-
2023
- 2023-08-28 ZA ZA2023/08288A patent/ZA202308288B/en unknown
Also Published As
Publication number | Publication date |
---|---|
WO2022160898A1 (zh) | 2022-08-04 |
ZA202308288B (en) | 2023-09-27 |
US20240104885A1 (en) | 2024-03-28 |
CN112884022A (zh) | 2021-06-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
McNeely-White et al. | Inception and ResNet features are (almost) equivalent | |
Khosla et al. | Enhancing performance of deep learning models with different data augmentation techniques: A survey | |
Gao et al. | Multiscale residual network with mixed depthwise convolution for hyperspectral image classification | |
Li et al. | Automatic fabric defect detection with a wide-and-compact network | |
He et al. | Supercnn: A superpixelwise convolutional neural network for salient object detection | |
CN106547880B (zh) | 一种融合地理区域知识的多维度地理场景识别方法 | |
Chen et al. | Semantic image segmentation with deep convolutional nets and fully connected crfs | |
CN106127197B (zh) | 基于显著标签排序的图像显著性目标检测方法和装置 | |
Qin et al. | Cross-domain collaborative learning via cluster canonical correlation analysis and random walker for hyperspectral image classification | |
CN108932518B (zh) | 一种基于视觉词袋模型的鞋印图像特征提取及检索方法 | |
CN108416270A (zh) | 一种基于多属性联合特征的交通标志识别方法 | |
CN112488229A (zh) | 一种基于特征分离和对齐的域自适应无监督目标检测方法 | |
CN109472733A (zh) | 基于卷积神经网络的图像隐写分析方法 | |
Manohar et al. | Convolutional neural network with SVM for classification of animal images | |
Liang et al. | Cross-scene foreground segmentation with supervised and unsupervised model communication | |
Bappy et al. | Real estate image classification | |
CN116091946A (zh) | 一种基于YOLOv5的无人机航拍图像目标检测方法 | |
CN112884022B (zh) | 一种基于图像平移的无监督深度表征学习方法及系统 | |
CN111310820A (zh) | 基于交叉验证深度cnn特征集成的地基气象云图分类方法 | |
CN113344069B (zh) | 一种基于多维关系对齐的无监督视觉表征学习的图像分类方法 | |
Vijayalakshmi K et al. | Copy-paste forgery detection using deep learning with error level analysis | |
CN115861306B (zh) | 一种基于自监督拼图模块的工业品异常检测方法 | |
Jia et al. | A mix-supervised unified framework for salient object detection | |
Lam et al. | Statistical bootstrap-based principal mode component analysis for dynamic background subtraction | |
CN111046869B (zh) | 一种基于深度学习的显著区域提取方法及系统 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
EE01 | Entry into force of recordation of patent licensing contract | ||
EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20210601 Assignee: Shaanxi Hao'an Occupational Health Technology Service Co.,Ltd. Huzhou Branch Assignor: ZHEJIANG NORMAL University Contract record no.: X2023980045423 Denomination of invention: An unsupervised deep representation learning method and system based on image translation Granted publication date: 20211112 License type: Common License Record date: 20231101 Application publication date: 20210601 Assignee: ZHEJIANG HUABAO INK Co.,Ltd. Assignor: ZHEJIANG NORMAL University Contract record no.: X2023980045391 Denomination of invention: An unsupervised deep representation learning method and system based on image translation Granted publication date: 20211112 License type: Common License Record date: 20231101 |
|
EE01 | Entry into force of recordation of patent licensing contract | ||
EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20210601 Assignee: Huzhou Zhiying Stationery Supplies Co.,Ltd. Assignor: ZHEJIANG NORMAL University Contract record no.: X2023980045739 Denomination of invention: An unsupervised deep representation learning method and system based on image translation Granted publication date: 20211112 License type: Common License Record date: 20231106 |
|
EE01 | Entry into force of recordation of patent licensing contract | ||
EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20210601 Assignee: Ningbo Beilun Qiancai Printing Equipment Co.,Ltd. Assignor: ZHEJIANG NORMAL University Contract record no.: X2024980000675 Denomination of invention: An unsupervised deep representation learning method and system based on image translation Granted publication date: 20211112 License type: Common License Record date: 20240115 |