CN112020723A - 用于语义分割的分类神经网络的训练方法及装置、电子设备 - Google Patents
用于语义分割的分类神经网络的训练方法及装置、电子设备 Download PDFInfo
- Publication number
- CN112020723A CN112020723A CN201880092697.6A CN201880092697A CN112020723A CN 112020723 A CN112020723 A CN 112020723A CN 201880092697 A CN201880092697 A CN 201880092697A CN 112020723 A CN112020723 A CN 112020723A
- Authority
- CN
- China
- Prior art keywords
- training
- images
- neural network
- image
- training images
- 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.)
- Pending
Links
- 238000012549 training Methods 0.000 title claims abstract description 249
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 title claims abstract description 52
- 230000011218 segmentation Effects 0.000 title abstract description 23
- 238000012360 testing method Methods 0.000 claims description 39
- 238000012545 processing Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000012935 Averaging Methods 0.000 claims description 4
- 230000009467 reduction Effects 0.000 abstract description 7
- 238000004364 calculation method Methods 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 21
- 230000006870 function Effects 0.000 description 7
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000004075 alteration Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
Images
Classifications
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
一种用于语义分割的分类神经网络的训练装置及方法、电子设备。即使在训练网络时使用了较多数量的训练图像，由于在每次训练时能够部分利用之前训练时已经获得的梯度，因此能够有效减少计算量并适用于硬件资源有限的情况，并且，由于计算量的减少，训练速度加快，能够缩短训练完成的时间，另外，由于每次训练时都使用了新的数据，使得在使用有限的硬件资源的条件下仍然能够保证训练的精度。
Description
PCT国内申请，说明书已公开。
Claims (15)
- PCT国内申请，权利要求书已公开。
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2018/087956 WO2019222936A1 (zh) | 2018-05-23 | 2018-05-23 | 用于语义分割的分类神经网络的训练方法及装置、电子设备 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112020723A true CN112020723A (zh) | 2020-12-01 |
Family
ID=68615537
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201880092697.6A Pending CN112020723A (zh) | 2018-05-23 | 2018-05-23 | 用于语义分割的分类神经网络的训练方法及装置、电子设备 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112020723A (zh) |
| WO (1) | WO2019222936A1 (zh) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111783782B (zh) * | 2020-05-29 | 2022-08-05 | 河海大学 | 融合改进UNet和SegNet的遥感图像语义分割方法 |
| CN111818557B (zh) * | 2020-08-04 | 2023-02-28 | 中国联合网络通信集团有限公司 | 网络覆盖问题识别方法、装置及系统 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105488515A (zh) * | 2014-09-17 | 2016-04-13 | 富士通株式会社 | 训练卷积神经网路分类器的方法和图像处理装置 |
| CN105512684A (zh) * | 2015-12-09 | 2016-04-20 | 江苏大为科技股份有限公司 | 基于主成分分析卷积神经网络的车标自动识别方法 |
| CN105654176A (zh) * | 2014-11-14 | 2016-06-08 | 富士通株式会社 | 神经网络系统及神经网络系统的训练装置和方法 |
| US20170262735A1 (en) * | 2016-03-11 | 2017-09-14 | Kabushiki Kaisha Toshiba | Training constrained deconvolutional networks for road scene semantic segmentation |
| CN108062551A (zh) * | 2017-06-28 | 2018-05-22 | 浙江大学 | 一种基于邻接矩阵的图特征提取系统、图分类系统和方法 |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5359699A (en) * | 1991-12-02 | 1994-10-25 | General Electric Company | Method for using a feed forward neural network to perform classification with highly biased data |
| CN103440635B (zh) * | 2013-09-17 | 2016-06-22 | 厦门美图网科技有限公司 | 一种基于学习的对比度受限自适应直方图均衡方法 |
| CN104866900B (zh) * | 2015-01-29 | 2018-01-19 | 北京工业大学 | 一种反卷积神经网络训练方法 |
| CN105426930B (zh) * | 2015-11-09 | 2018-11-02 | 国网冀北电力有限公司信息通信分公司 | 一种基于卷积神经网络的变电站属性分割方法 |
| CN105389594B (zh) * | 2015-11-19 | 2020-10-27 | 联想(北京)有限公司 | 信息处理方法及电子设备 |
| CN106530305B (zh) * | 2016-09-23 | 2019-09-13 | 北京市商汤科技开发有限公司 | 语义分割模型训练和图像分割方法及装置、计算设备 |
-
2018
- 2018-05-23 WO PCT/CN2018/087956 patent/WO2019222936A1/zh active Application Filing
- 2018-05-23 CN CN201880092697.6A patent/CN112020723A/zh active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105488515A (zh) * | 2014-09-17 | 2016-04-13 | 富士通株式会社 | 训练卷积神经网路分类器的方法和图像处理装置 |
| CN105654176A (zh) * | 2014-11-14 | 2016-06-08 | 富士通株式会社 | 神经网络系统及神经网络系统的训练装置和方法 |
| CN105512684A (zh) * | 2015-12-09 | 2016-04-20 | 江苏大为科技股份有限公司 | 基于主成分分析卷积神经网络的车标自动识别方法 |
| US20170262735A1 (en) * | 2016-03-11 | 2017-09-14 | Kabushiki Kaisha Toshiba | Training constrained deconvolutional networks for road scene semantic segmentation |
| CN108062551A (zh) * | 2017-06-28 | 2018-05-22 | 浙江大学 | 一种基于邻接矩阵的图特征提取系统、图分类系统和方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019222936A1 (zh) | 2019-11-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3046320B1 (en) | Method for generating an hdr image of a scene based on a tradeoff between brightness distribution and motion | |
| CN111950723B (zh) | 神经网络模型训练方法、图像处理方法、装置及终端设备 | |
| US20110211233A1 (en) | Image processing device, image processing method and computer program | |
| CN110263699B (zh) | 视频图像处理方法、装置、设备及存储介质 | |
| US8300969B2 (en) | Image processing apparatus and method, and program | |
| US7596273B2 (en) | Image processing method, image processing apparatus, and image processing program | |
| CN110114801B (zh) | 图像前景检测装置及方法、电子设备 | |
| CN112020723A (zh) | 用于语义分割的分类神经网络的训练方法及装置、电子设备 | |
| JP5937823B2 (ja) | 画像照合処理装置、画像照合処理方法及び画像照合処理プログラム | |
| EP2790154A1 (en) | Method and apparatus for determining an alpha value for alpha matting | |
| CN112188236B (zh) | 视频插帧模型训练、视频插帧生成方法及相关装置 | |
| CN112052949B (zh) | 基于迁移学习的图像处理方法、装置、设备和存储介质 | |
| CN111931698B (zh) | 基于小型训练集的图像深度学习网络构建方法及装置 | |
| EP3840381A1 (en) | Method and device for detecting video scene change, and video acquisition device | |
| CN109218728B (zh) | 一种场景切换检测方法和系统 | |
| CN109167919B (zh) | 一种图片压缩方法及装置 | |
| US20120200748A1 (en) | Image processing apparatus, electronic camera, and storage medium storing image processing program | |
| CN116385369A (zh) | 深度图像质量评价方法、装置、电子设备及存储介质 | |
| CN111064897B (zh) | 一种曝光评估值的统计方法及成像设备 | |
| WO2017166585A1 (zh) | 视频转场判断方法、装置和电子设备 | |
| CN112020721A (zh) | 用于语义分割的分类神经网络的训练方法及装置、电子设备 | |
| CN113938671A (zh) | 图像内容分析方法、装置、电子设备和存储介质 | |
| Ye et al. | Accurate single-image defocus deblurring based on improved integration with defocus map estimation | |
| CN112200730A (zh) | 图像滤波处理方法、装置、设备及存储介质 | |
| CN111310657B (zh) | 驾驶员人脸监控方法、装置、终端和计算机可读存储介质 |
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 |