CN111033523B - 用于图像分类任务的数据增强 - Google Patents

用于图像分类任务的数据增强 Download PDF

Info

Publication number
CN111033523B
CN111033523B CN201880054715.1A CN201880054715A CN111033523B CN 111033523 B CN111033523 B CN 111033523B CN 201880054715 A CN201880054715 A CN 201880054715A CN 111033523 B CN111033523 B CN 111033523B
Authority
CN
China
Prior art keywords
image
machine learning
computer
training
learning process
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
Application number
CN201880054715.1A
Other languages
English (en)
Chinese (zh)
Other versions
CN111033523A (zh
Inventor
井上拓
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.)
International Business Machines Corp
Original Assignee
International Business Machines Corp
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 International Business Machines Corp filed Critical International Business Machines Corp
Publication of CN111033523A publication Critical patent/CN111033523A/zh
Application granted granted Critical
Publication of CN111033523B publication Critical patent/CN111033523B/zh
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
    • G06F18/2155—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the incorporation of unlabelled data, e.g. multiple instance learning [MIL], semi-supervised techniques using expectation-maximisation [EM] or naïve labelling
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • G06F18/24155—Bayesian classification
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/09—Supervised learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/29—Graphical models, e.g. Bayesian networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20076—Probabilistic image processing
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computational Linguistics (AREA)
  • Databases & Information Systems (AREA)
  • Mathematical Physics (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Multimedia (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Medical Informatics (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Image Analysis (AREA)
CN201880054715.1A 2017-09-21 2018-09-20 用于图像分类任务的数据增强 Active CN111033523B (zh)

Applications Claiming Priority (5)

Application Number Priority Date Filing Date Title
US15/711,756 2017-09-21
US15/711,756 US10496902B2 (en) 2017-09-21 2017-09-21 Data augmentation for image classification tasks
US15/843,687 US10614346B2 (en) 2017-09-21 2017-12-15 Data augmentation for image classification tasks
US15/843,687 2017-12-15
PCT/IB2018/057257 WO2019058300A1 (en) 2017-09-21 2018-09-20 INCREASING DATA FOR IMAGE CLASSIFICATION TASKS

Publications (2)

Publication Number Publication Date
CN111033523A CN111033523A (zh) 2020-04-17
CN111033523B true CN111033523B (zh) 2023-12-29

Family

ID=65719394

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201880054715.1A Active CN111033523B (zh) 2017-09-21 2018-09-20 用于图像分类任务的数据增强

Country Status (5)

Country Link
US (4) US10496902B2 (https=)
JP (1) JP7034265B2 (https=)
CN (1) CN111033523B (https=)
GB (1) GB2580002B (https=)
WO (1) WO2019058300A1 (https=)

Families Citing this family (26)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10496902B2 (en) * 2017-09-21 2019-12-03 International Business Machines Corporation Data augmentation for image classification tasks
US10740400B2 (en) * 2018-08-28 2020-08-11 Google Llc Image analysis for results of textual image queries
US11544500B2 (en) * 2019-02-12 2023-01-03 International Business Machines Corporation Data augmentation for image classification tasks
CN109978071A (zh) * 2019-04-03 2019-07-05 西北工业大学 基于数据增广和分类器融合的高光谱图像分类方法
CN111798000A (zh) * 2019-04-09 2020-10-20 Oppo广东移动通信有限公司 数据优化方法、装置、存储介质及电子设备
EP3731155B1 (en) * 2019-04-25 2025-09-17 ABB Schweiz AG Apparatus and method for drive selection using machine learning
US11520521B2 (en) * 2019-06-20 2022-12-06 Western Digital Technologies, Inc. Storage controller having data augmentation components for use with non-volatile memory die
WO2021006622A1 (en) 2019-07-09 2021-01-14 Samsung Electronics Co., Ltd. Electronic apparatus and controlling method thereof
CN110796176B (zh) * 2019-10-09 2022-12-16 武汉大学 一种基于像素对和加权投票的高分辨率影像分类方法和系统
CN111275080B (zh) * 2020-01-14 2021-01-08 腾讯科技（深圳）有限公司 基于人工智能的图像分类模型训练方法、分类方法及装置
CN111507378A (zh) * 2020-03-24 2020-08-07 华为技术有限公司 训练图像处理模型的方法和装置
KR102528405B1 (ko) * 2020-04-08 2023-05-02 에스케이텔레콤 주식회사 이미지를 분류하도록 훈련된 신경망을 이용하는 이미지 분류 장치 및 방법
CA3166581A1 (en) * 2020-05-22 2021-11-25 Parisa Darvish Zadeh Varcheie Method and system for training inspection equipment for automatic defect classification
CN111885280B (zh) * 2020-07-17 2021-04-13 电子科技大学 一种混合卷积神经网络视频编码环路滤波方法
US12159213B2 (en) 2020-11-04 2024-12-03 Intrinsic Innovation Llc Source-agnostic image processing
US11170581B1 (en) * 2020-11-12 2021-11-09 Intrinsic Innovation Llc Supervised domain adaptation
US20240005643A1 (en) * 2020-12-09 2024-01-04 Sony Group Corporation Information processing apparatus, information processing method, computer program, imaging device, vehicle device, and medical robot device
CN114691912A (zh) 2020-12-25 2022-07-01 日本电气株式会社 图像处理的方法、设备和计算机可读存储介质
US12266098B2 (en) * 2021-11-11 2025-04-01 International Business Machines Corporation Improving model performance by artificial blending of healthy tissue
CN116318481A (zh) * 2021-12-20 2023-06-23 华为技术有限公司 一种通信方法及装置
US20230205873A1 (en) * 2021-12-29 2023-06-29 Micron Technology, Inc. Training procedure change determination to detect attack
CN116523760A (zh) * 2022-01-21 2023-08-01 戴尔产品有限公司 数据增强的方法、设备和计算机程序产品
JP7815035B2 (ja) * 2022-06-01 2026-02-17 株式会社東芝 表現学習装置、方法及びプログラム
KR102898537B1 (ko) * 2022-07-05 2025-12-10 광주과학기술원 미분류 데이터를 이용하여 신경망의 학습을 조기 종료하는 방법
CN115618962B (zh) * 2022-10-18 2023-05-23 支付宝(杭州)信息技术有限公司 一种模型训练的方法、业务风控的方法及装置
US12586356B2 (en) 2023-02-02 2026-03-24 Ford Global Technologies, Llc Artificial image generation with traffic signs

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101452575A (zh) * 2008-12-12 2009-06-10 北京航空航天大学 一种基于神经网络的图像自适应增强方法
CN104318266A (zh) * 2014-10-19 2015-01-28 温州大学 一种图像智能分析处理预警方法
CN106709907A (zh) * 2016-12-08 2017-05-24 上海联影医疗科技有限公司 Mr图像的处理方法及装置
CN106934815A (zh) * 2017-02-27 2017-07-07 南京理工大学 基于混合区域的活动轮廓模型图像分割方法
CN107169939A (zh) * 2017-05-31 2017-09-15 广东欧珀移动通信有限公司 图像处理方法及相关产品

Family Cites Families (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8416847B2 (en) * 1998-12-21 2013-04-09 Zin Stai Pte. In, Llc Separate plane compression using plurality of compression methods including ZLN and ZLD methods
US7082211B2 (en) * 2002-05-31 2006-07-25 Eastman Kodak Company Method and system for enhancing portrait images
US8873813B2 (en) * 2012-09-17 2014-10-28 Z Advanced Computing, Inc. Application of Z-webs and Z-factors to analytics, search engine, learning, recognition, natural language, and other utilities
US9418467B2 (en) 2012-12-21 2016-08-16 Honda Motor Co., Ltd. 3D human models applied to pedestrian pose classification
CN103310229B (zh) 2013-06-15 2016-09-07 浙江大学 一种用于图像分类的多任务机器学习方法及其装置
US9536293B2 (en) 2014-07-30 2017-01-03 Adobe Systems Incorporated Image assessment using deep convolutional neural networks
GB2532075A (en) * 2014-11-10 2016-05-11 Lego As System and method for toy recognition and detection based on convolutional neural networks
US20160140438A1 (en) 2014-11-13 2016-05-19 Nec Laboratories America, Inc. Hyper-class Augmented and Regularized Deep Learning for Fine-grained Image Classification
EP3029606A3 (en) 2014-11-14 2016-09-14 Thomson Licensing Method and apparatus for image classification with joint feature adaptation and classifier learning
US9501707B2 (en) * 2015-04-16 2016-11-22 Xerox Corporation Method and system for bootstrapping an OCR engine for license plate recognition
CN106296623B (zh) * 2015-06-10 2019-07-05 腾讯科技（深圳）有限公司 一种图片处理方法及装置
US10176642B2 (en) * 2015-07-17 2019-01-08 Bao Tran Systems and methods for computer assisted operation
US9684967B2 (en) 2015-10-23 2017-06-20 International Business Machines Corporation Imaging segmentation using multi-scale machine learning approach
US10068171B2 (en) 2015-11-12 2018-09-04 Conduent Business Services, Llc Multi-layer fusion in a convolutional neural network for image classification
US9721334B2 (en) * 2015-12-03 2017-08-01 International Business Machines Corporation Work-piece defect inspection via optical images and CT images
US10373073B2 (en) 2016-01-11 2019-08-06 International Business Machines Corporation Creating deep learning models using feature augmentation
US9864931B2 (en) * 2016-04-13 2018-01-09 Conduent Business Services, Llc Target domain characterization for data augmentation
CN106169081B (zh) 2016-06-29 2019-07-05 北京工业大学 一种基于不同照度的图像分类及处理方法
US20180137391A1 (en) * 2016-11-13 2018-05-17 Imagry (Israel) Ltd. System and method for training image classifier
JP2019003565A (ja) 2017-06-19 2019-01-10 コニカミノルタ株式会社 画像処理装置、画像処理方法、及び画像処理プログラム
US10496902B2 (en) * 2017-09-21 2019-12-03 International Business Machines Corporation Data augmentation for image classification tasks

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101452575A (zh) * 2008-12-12 2009-06-10 北京航空航天大学 一种基于神经网络的图像自适应增强方法
CN104318266A (zh) * 2014-10-19 2015-01-28 温州大学 一种图像智能分析处理预警方法
CN106709907A (zh) * 2016-12-08 2017-05-24 上海联影医疗科技有限公司 Mr图像的处理方法及装置
CN106934815A (zh) * 2017-02-27 2017-07-07 南京理工大学 基于混合区域的活动轮廓模型图像分割方法
CN107169939A (zh) * 2017-05-31 2017-09-15 广东欧珀移动通信有限公司 图像处理方法及相关产品

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
雾天视频图像增强与运动目标跟踪模型及方法;钟锦;吴昊;;计算机仿真(第08期);第1-7页 *

Also Published As

Publication number Publication date
US11238317B2 (en) 2022-02-01
US10614346B2 (en) 2020-04-07
US11120309B2 (en) 2021-09-14
US20190087694A1 (en) 2019-03-21
US20200175343A1 (en) 2020-06-04
GB2580002B (en) 2021-01-13
US20200082229A1 (en) 2020-03-12
US20190087695A1 (en) 2019-03-21
CN111033523A (zh) 2020-04-17
WO2019058300A1 (en) 2019-03-28
GB2580002A (en) 2020-07-08
US10496902B2 (en) 2019-12-03
JP7034265B2 (ja) 2022-03-11
JP2020534594A (ja) 2020-11-26
GB202005186D0 (en) 2020-05-20

Similar Documents

Publication Publication Date Title
CN111033523B (zh) 用于图像分类任务的数据增强
US10885111B2 (en) Generating cross-domain data using variational mapping between embedding spaces
US11521090B2 (en) Collaborative distributed machine learning
US10430250B2 (en) Decomposing monolithic application into microservices
US10503827B2 (en) Supervised training for word embedding
US10592635B2 (en) Generating synthetic layout patterns by feedforward neural network based variational autoencoders
CN112333623A (zh) 使用图像信息的基于空间的音频对象生成
US11544500B2 (en) Data augmentation for image classification tasks
CN111489794B (zh) 用于创建预测模型的方法
US10915529B2 (en) Selecting an optimal combination of systems for query processing
US20220358358A1 (en) Accelerating inference of neural network models via dynamic early exits
US11430176B2 (en) Generating volume predictions of three-dimensional volumes using slice features
US20180068330A1 (en) Deep Learning Based Unsupervised Event Learning for Economic Indicator Predictions
US11676032B2 (en) Sim-to-real learning of 2D multiple sound source localization
US11308414B2 (en) Multi-step ahead forecasting using complex-valued vector autoregregression
US11704542B2 (en) Convolutional dynamic Boltzmann Machine for temporal event sequence
US11823039B2 (en) Safe and fast exploration for reinforcement learning using constrained action manifolds
US20230177355A1 (en) Automated fairness-driven graph node label classification
US10530842B2 (en) Domain-specific pattern design
US20220036245A1 (en) EXTRACTING SEQUENCES FROM d-DIMENSIONAL INPUT DATA FOR SEQUENTIAL PROCESSING WITH NEURAL NETWORKS
US10791398B1 (en) Feature processing for multi-array sound applications with deep learning and limited data

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