CN107122809B - 基于图像自编码的神经网络特征学习方法 - Google Patents
基于图像自编码的神经网络特征学习方法 Download PDFInfo
- Publication number
- CN107122809B CN107122809B CN201710271606.2A CN201710271606A CN107122809B CN 107122809 B CN107122809 B CN 107122809B CN 201710271606 A CN201710271606 A CN 201710271606A CN 107122809 B CN107122809 B CN 107122809B
- Authority
- CN
- China
- Prior art keywords
- image
- neural network
- training
- self
- coding
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000012549 training Methods 0.000 claims abstract description 78
- 239000013598 vector Substances 0.000 claims abstract description 51
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 40
- 230000011218 segmentation Effects 0.000 claims abstract description 35
- 238000012360 testing method Methods 0.000 claims abstract description 25
- 238000011478 gradient descent method Methods 0.000 claims abstract description 3
- 230000014509 gene expression Effects 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 12
- 238000003062 neural network model Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 239000003086 colorant Substances 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 2
- 210000002569 neuron Anatomy 0.000 claims description 2
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract 1
- 238000013135 deep learning Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000011160 research Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013529 biological neural network Methods 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
- G06V30/192—Recognition using electronic means using simultaneous comparisons or correlations of the image signals with a plurality of references
- G06V30/194—References adjustable by an adaptive method, e.g. learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5838—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
- G06V10/464—Salient features, e.g. scale invariant feature transforms [SIFT] using a plurality of salient features, e.g. bag-of-words [BoW] representations
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
Description
Layer | Configuration |
conv1 | filter 96×11×11,stride 4×4,pad 0,LRN,pool 3×3,stride2×2 |
conv2 | filter 256×5×5,stride 1×1,pad 2,LRN,pool 3×3,stride 2×2 |
conv3 | filter 384×3×3,stride 1×1,pad 1 |
conv4 | filter 384×3×3,stride 1×1,pad 1 |
conv5 | filter 256×3×3,stride 1×1,pad 1,pool 2×2,stride 2×2 |
full6 | fc 4096 |
full7 | fc 4096 |
full8 | fc h |
Claims (2)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710271606.2A CN107122809B (zh) | 2017-04-24 | 2017-04-24 | 基于图像自编码的神经网络特征学习方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710271606.2A CN107122809B (zh) | 2017-04-24 | 2017-04-24 | 基于图像自编码的神经网络特征学习方法 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107122809A CN107122809A (zh) | 2017-09-01 |
CN107122809B true CN107122809B (zh) | 2020-04-28 |
Family
ID=59725779
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710271606.2A Active CN107122809B (zh) | 2017-04-24 | 2017-04-24 | 基于图像自编码的神经网络特征学习方法 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107122809B (zh) |
Families Citing this family (41)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9947103B1 (en) * | 2017-10-03 | 2018-04-17 | StradVision, Inc. | Learning method and learning device for improving image segmentation and testing method and testing device using the same |
CN109685087B9 (zh) * | 2017-10-18 | 2023-02-03 | 富士通株式会社 | 信息处理方法和装置以及信息检测方法 |
CN107578300A (zh) * | 2017-10-24 | 2018-01-12 | 济南浪潮高新科技投资发展有限公司 | 一种电梯广告投放工作自动审核的方法及装置 |
CN107766893B (zh) * | 2017-11-03 | 2021-01-22 | 电子科技大学 | 基于标签多级编码神经网络的目标识别方法 |
CN107870321B (zh) * | 2017-11-03 | 2020-12-29 | 电子科技大学 | 基于伪标签学习的雷达一维距离像目标识别方法 |
CN108090117B (zh) | 2017-11-06 | 2019-03-19 | 北京三快在线科技有限公司 | 一种图像检索方法及装置,电子设备 |
CN107657615B (zh) * | 2017-11-10 | 2019-07-23 | 西安电子科技大学 | 基于增量cae的高分辨sar图像变化检测方法 |
US10748036B2 (en) | 2017-11-21 | 2020-08-18 | Nvidia Corporation | Training a neural network to predict superpixels using segmentation-aware affinity loss |
CN108445752B (zh) * | 2018-03-02 | 2021-08-17 | 北京工业大学 | 一种自适应选择深度特征的随机权神经网络集成建模方法 |
CN108536769B (zh) * | 2018-03-22 | 2023-01-03 | 深圳市安软慧视科技有限公司 | 图像分析方法、搜索方法及装置、计算机装置及存储介质 |
EP3567548B1 (en) * | 2018-05-09 | 2020-06-24 | Siemens Healthcare GmbH | Medical image segmentation |
CN108710866B (zh) * | 2018-06-04 | 2024-02-20 | 平安科技(深圳)有限公司 | 汉字模型训练方法、汉字识别方法、装置、设备及介质 |
CN109086652A (zh) * | 2018-06-04 | 2018-12-25 | 平安科技(深圳)有限公司 | 手写字模型训练方法、汉字识别方法、装置、设备及介质 |
CN108765423B (zh) * | 2018-06-20 | 2020-07-28 | 北京七鑫易维信息技术有限公司 | 一种卷积神经网络训练方法及装置 |
CN109102064B (zh) * | 2018-06-26 | 2020-11-13 | 杭州雄迈集成电路技术股份有限公司 | 一种高精度的神经网络量化压缩方法 |
CN109241816B (zh) * | 2018-07-02 | 2020-10-27 | 北京交通大学 | 一种基于标签优化的图像再识别系统及损失函数确定方法 |
CN110858812B (zh) * | 2018-08-24 | 2021-07-13 | 中国移动通信集团浙江有限公司 | 网元割接值守方法及装置 |
CN109657082B (zh) * | 2018-08-28 | 2022-11-29 | 武汉大学 | 基于全卷积神经网络的遥感图像多标签检索方法及系统 |
CN111104834A (zh) * | 2018-10-25 | 2020-05-05 | 南京大学 | 一种交叉对比神经网络在心声智能检测中的应用方法 |
CN109472360B (zh) | 2018-10-30 | 2020-09-04 | 北京地平线机器人技术研发有限公司 | 神经网络的更新方法、更新装置和电子设备 |
CN111161363A (zh) * | 2018-11-07 | 2020-05-15 | 合肥图鸭信息科技有限公司 | 一种图像编码模型训练方法及装置 |
EP3675061A1 (en) * | 2018-12-29 | 2020-07-01 | Dassault Systèmes | Forming a dataset for inference of editable feature trees |
CN112020724A (zh) * | 2019-04-01 | 2020-12-01 | 谷歌有限责任公司 | 学习可压缩的特征 |
CN110119447B (zh) * | 2019-04-26 | 2023-06-16 | 平安科技(深圳)有限公司 | 自编码神经网络处理方法、装置、计算机设备及存储介质 |
CN110070140B (zh) * | 2019-04-28 | 2021-03-23 | 清华大学 | 基于多类别信息的用户相似性确定方法及装置 |
CN110263029B (zh) * | 2019-05-06 | 2023-06-23 | 平安科技(深圳)有限公司 | 数据库生成测试数据的方法、装置、终端及介质 |
CN110188231A (zh) * | 2019-06-11 | 2019-08-30 | 上海德拓信息技术股份有限公司 | 图片中相似物体检索方法及装置 |
CN110517759B (zh) * | 2019-08-29 | 2022-03-25 | 腾讯医疗健康(深圳)有限公司 | 一种待标注图像确定的方法、模型训练的方法及装置 |
CN110830807B (zh) * | 2019-11-04 | 2022-08-23 | 腾讯科技(深圳)有限公司 | 图像压缩方法、装置及存储介质 |
CN111414510A (zh) * | 2020-03-24 | 2020-07-14 | 北京曲线智能装备有限公司 | 一种快速图像检索方法 |
CN111738318B (zh) * | 2020-06-11 | 2022-09-30 | 大连理工大学 | 一种基于图神经网络的超大图像分类方法 |
CN111813830B (zh) * | 2020-07-02 | 2023-03-28 | 清华大学 | 一种基于轨道交通工业互联网的工业时序数据检索方法 |
CN111859790B (zh) * | 2020-07-08 | 2022-09-16 | 大连理工大学 | 一种基于图像特征学习的曲线加筋结构布局智能设计方法 |
CN112016599B (zh) * | 2020-08-13 | 2023-09-15 | 驭势科技(浙江)有限公司 | 用于图像检索的神经网络训练方法、装置及电子设备 |
CN111985161B (zh) * | 2020-08-21 | 2024-06-14 | 广东电网有限责任公司清远供电局 | 一种变电站三维模型重构方法 |
CN112150338B (zh) * | 2020-09-21 | 2023-12-05 | 清华大学 | 一种神经网络模型图像水印的去除方法 |
CN113449737B (zh) * | 2021-05-27 | 2023-11-17 | 南京大学 | 一种基于自编码器的单探头声学成像方法及装置 |
CN113780450B (zh) * | 2021-09-16 | 2023-07-28 | 郑州云智信安安全技术有限公司 | 基于自编码神经网络的分布式存储方法及系统 |
CN114863178A (zh) * | 2022-05-13 | 2022-08-05 | 南京大学 | 面向神经网络视觉系统的图像数据输入检测方法和系统 |
CN115337026B (zh) * | 2022-10-19 | 2023-03-10 | 之江实验室 | 一种基于卷积神经网络的eeg信号特征检索方法、装置 |
CN116524282B (zh) * | 2023-06-26 | 2023-09-05 | 贵州大学 | 一种基于特征向量的离散相似度匹配分类方法 |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104077599A (zh) * | 2014-07-04 | 2014-10-01 | 西安电子科技大学 | 基于深度神经网络的极化sar图像分类方法 |
WO2014205231A1 (en) * | 2013-06-19 | 2014-12-24 | The Regents Of The University Of Michigan | Deep learning framework for generic object detection |
CN105243154A (zh) * | 2015-10-27 | 2016-01-13 | 武汉大学 | 基于显著点特征和稀疏自编码的遥感图像检索方法及系统 |
CN105930770A (zh) * | 2016-04-13 | 2016-09-07 | 重庆邮电大学 | 一种基于高斯过程隐变量模型的人体动作识别方法 |
CN106446895A (zh) * | 2016-10-28 | 2017-02-22 | 安徽四创电子股份有限公司 | 一种基于深度卷积神经网络的车牌识别方法 |
CN106503654A (zh) * | 2016-10-24 | 2017-03-15 | 中国地质大学(武汉) | 一种基于深度稀疏自编码网络的人脸情感识别方法 |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102288280B1 (ko) * | 2014-11-05 | 2021-08-10 | 삼성전자주식회사 | 영상 학습 모델을 이용한 영상 생성 방법 및 장치 |
US10552730B2 (en) * | 2015-06-30 | 2020-02-04 | Adobe Inc. | Procedural modeling using autoencoder neural networks |
-
2017
- 2017-04-24 CN CN201710271606.2A patent/CN107122809B/zh active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014205231A1 (en) * | 2013-06-19 | 2014-12-24 | The Regents Of The University Of Michigan | Deep learning framework for generic object detection |
CN104077599A (zh) * | 2014-07-04 | 2014-10-01 | 西安电子科技大学 | 基于深度神经网络的极化sar图像分类方法 |
CN105243154A (zh) * | 2015-10-27 | 2016-01-13 | 武汉大学 | 基于显著点特征和稀疏自编码的遥感图像检索方法及系统 |
CN105930770A (zh) * | 2016-04-13 | 2016-09-07 | 重庆邮电大学 | 一种基于高斯过程隐变量模型的人体动作识别方法 |
CN106503654A (zh) * | 2016-10-24 | 2017-03-15 | 中国地质大学(武汉) | 一种基于深度稀疏自编码网络的人脸情感识别方法 |
CN106446895A (zh) * | 2016-10-28 | 2017-02-22 | 安徽四创电子股份有限公司 | 一种基于深度卷积神经网络的车牌识别方法 |
Also Published As
Publication number | Publication date |
---|---|
CN107122809A (zh) | 2017-09-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107122809B (zh) | 基于图像自编码的神经网络特征学习方法 | |
Kukačka et al. | Regularization for deep learning: A taxonomy | |
CN113190699B (zh) | 一种基于类别级语义哈希的遥感图像检索方法及装置 | |
Wu et al. | Application of image retrieval based on convolutional neural networks and Hu invariant moment algorithm in computer telecommunications | |
CN108121975B (zh) | 一种联合原始数据和生成数据的人脸识别方法 | |
Wang et al. | Deep learning for image retrieval: What works and what doesn't | |
Ning et al. | Semantics-consistent representation learning for remote sensing image–voice retrieval | |
CN111414461A (zh) | 一种融合知识库与用户建模的智能问答方法及系统 | |
CN110598022B (zh) | 一种基于鲁棒深度哈希网络的图像检索系统与方法 | |
CN111079514A (zh) | 一种基于clbp和卷积神经网络的人脸识别方法 | |
CN112949740A (zh) | 一种基于多级度量的小样本图像分类方法 | |
CN111008224A (zh) | 一种基于深度多任务表示学习的时间序列分类和检索方法 | |
CN111695455B (zh) | 一种基于耦合判别流形对齐的低分辨人脸识别方法 | |
CN112883931A (zh) | 基于长短期记忆网络的实时真假运动判断方法 | |
CN108388918B (zh) | 具有结构保持特性的数据特征选择方法 | |
Peng et al. | A survey: Image classification models based on convolutional neural networks | |
Wang et al. | A convolutional neural network image classification based on extreme learning machine | |
Zeng et al. | Flower image classification based on an improved lightweight neural network with multi-scale feature fusion and attention mechanism | |
CN115100694A (zh) | 一种基于自监督神经网络的指纹快速检索方法 | |
CN112650877B (zh) | 一种基于改进的深度残差卷积神经网络和深度哈希的高清遥感图像快速检索方法 | |
CN112801153B (zh) | 一种嵌入lbp特征的图的半监督图像分类方法及系统 | |
CN111767825B (zh) | 一种人脸属性不变鲁棒性人脸识别方法及系统 | |
Lei et al. | Student action recognition based on multiple features | |
CN113869454A (zh) | 一种基于快速嵌入式谱分析的高光谱图像稀疏特征选择方法 | |
Wang et al. | Image target recognition based on improved convolutional neural network |
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 |
Application publication date: 20170901 Assignee: Henan zhuodoo Information Technology Co.,Ltd. Assignor: Beijing University of Technology Contract record no.: X2024980000138 Denomination of invention: A Neural Network Feature Learning Method Based on Image Self encoding Granted publication date: 20200428 License type: Common License Record date: 20240104 Application publication date: 20170901 Assignee: Luoyang Lexiang Network Technology Co.,Ltd. Assignor: Beijing University of Technology Contract record no.: X2024980000083 Denomination of invention: A Neural Network Feature Learning Method Based on Image Self encoding Granted publication date: 20200428 License type: Common License Record date: 20240104 |
|
EE01 | Entry into force of recordation of patent licensing contract |