CN115482418B - 基于伪负标签的半监督模型训练方法、系统及应用 - Google Patents
基于伪负标签的半监督模型训练方法、系统及应用 Download PDFInfo
- Publication number
- CN115482418B CN115482418B CN202211232414.8A CN202211232414A CN115482418B CN 115482418 B CN115482418 B CN 115482418B CN 202211232414 A CN202211232414 A CN 202211232414A CN 115482418 B CN115482418 B CN 115482418B
- Authority
- CN
- China
- Prior art keywords
- pseudo
- label
- classification
- result
- model
- 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
- 238000012549 training Methods 0.000 title claims abstract description 88
- 238000000034 method Methods 0.000 title claims abstract description 74
- 238000013145 classification model Methods 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 9
- 238000012804 iterative process Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000008878 coupling Effects 0.000 abstract description 4
- 238000010168 coupling process Methods 0.000 abstract description 4
- 238000005859 coupling reaction Methods 0.000 abstract description 4
- 238000012216 screening Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 6
- 238000004590 computer program Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000013519 translation Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
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
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (8)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211232414.8A CN115482418B (zh) | 2022-10-09 | 2022-10-09 | 基于伪负标签的半监督模型训练方法、系统及应用 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211232414.8A CN115482418B (zh) | 2022-10-09 | 2022-10-09 | 基于伪负标签的半监督模型训练方法、系统及应用 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115482418A CN115482418A (zh) | 2022-12-16 |
CN115482418B true CN115482418B (zh) | 2024-06-07 |
Family
ID=84393563
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211232414.8A Active CN115482418B (zh) | 2022-10-09 | 2022-10-09 | 基于伪负标签的半监督模型训练方法、系统及应用 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115482418B (zh) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115690100B (zh) * | 2022-12-28 | 2023-04-07 | 珠海横琴圣澳云智科技有限公司 | 半监督信号点检测模型训练方法、信号点检测方法和装置 |
CN116778239B (zh) * | 2023-06-16 | 2024-06-11 | 酷哇科技有限公司 | 面向实例分割模型的半监督训练方法及设备 |
CN117197474B (zh) * | 2023-09-28 | 2024-08-02 | 江苏开放大学(江苏城市职业学院) | 一种基于类别均衡及交叉合并策略的噪声标签学习方法 |
CN118334352B (zh) * | 2024-06-13 | 2024-08-13 | 宁波大学 | 一种点云语义分割模型的训练方法、系统、介质及设备 |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111078911A (zh) * | 2019-12-13 | 2020-04-28 | 宁波大学 | 一种基于自编码器的无监督哈希方法 |
KR20200046173A (ko) * | 2018-10-18 | 2020-05-07 | 부산대학교 산학협력단 | 언레이블 데이터를 사용한 나이브 반지도 심층 학습의 제공 방법 및 그 시스템 |
CN112232416A (zh) * | 2020-10-16 | 2021-01-15 | 浙江大学 | 一种基于伪标签加权的半监督学习方法 |
CN114037876A (zh) * | 2021-12-16 | 2022-02-11 | 马上消费金融股份有限公司 | 一种模型优化方法和装置 |
WO2022042002A1 (zh) * | 2020-08-31 | 2022-03-03 | 华为技术有限公司 | 一种半监督学习模型的训练方法、图像处理方法及设备 |
CN114648779A (zh) * | 2022-03-14 | 2022-06-21 | 宁波大学 | 基于自标签精炼深度学习模型的无监督行人重识别方法 |
CN114743109A (zh) * | 2022-04-28 | 2022-07-12 | 湖南大学 | 多模型协同优化高分遥感图像半监督变化检测方法及系统 |
CN114881149A (zh) * | 2022-05-10 | 2022-08-09 | 杭州海康威视数字技术股份有限公司 | 一种模型训练方法及装置、目标检测方法及装置 |
CN114943879A (zh) * | 2022-07-22 | 2022-08-26 | 中国科学院空天信息创新研究院 | 基于域适应半监督学习的sar目标识别方法 |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11694093B2 (en) * | 2018-03-14 | 2023-07-04 | Adobe Inc. | Generation of training data to train a classifier to identify distinct physical user devices in a cross-device context |
US11416772B2 (en) * | 2019-12-02 | 2022-08-16 | International Business Machines Corporation | Integrated bottom-up segmentation for semi-supervised image segmentation |
KR20210149530A (ko) * | 2020-06-02 | 2021-12-09 | 삼성에스디에스 주식회사 | 이미지 분류 모델 학습 방법 및 이를 수행하기 위한 장치 |
-
2022
- 2022-10-09 CN CN202211232414.8A patent/CN115482418B/zh active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20200046173A (ko) * | 2018-10-18 | 2020-05-07 | 부산대학교 산학협력단 | 언레이블 데이터를 사용한 나이브 반지도 심층 학습의 제공 방법 및 그 시스템 |
CN111078911A (zh) * | 2019-12-13 | 2020-04-28 | 宁波大学 | 一种基于自编码器的无监督哈希方法 |
WO2022042002A1 (zh) * | 2020-08-31 | 2022-03-03 | 华为技术有限公司 | 一种半监督学习模型的训练方法、图像处理方法及设备 |
CN112232416A (zh) * | 2020-10-16 | 2021-01-15 | 浙江大学 | 一种基于伪标签加权的半监督学习方法 |
CN114037876A (zh) * | 2021-12-16 | 2022-02-11 | 马上消费金融股份有限公司 | 一种模型优化方法和装置 |
CN114648779A (zh) * | 2022-03-14 | 2022-06-21 | 宁波大学 | 基于自标签精炼深度学习模型的无监督行人重识别方法 |
CN114743109A (zh) * | 2022-04-28 | 2022-07-12 | 湖南大学 | 多模型协同优化高分遥感图像半监督变化检测方法及系统 |
CN114881149A (zh) * | 2022-05-10 | 2022-08-09 | 杭州海康威视数字技术股份有限公司 | 一种模型训练方法及装置、目标检测方法及装置 |
CN114943879A (zh) * | 2022-07-22 | 2022-08-26 | 中国科学院空天信息创新研究院 | 基于域适应半监督学习的sar目标识别方法 |
Non-Patent Citations (5)
Title |
---|
Negative Pseudo Labeling using Class Proportion for Semantic Segmentation in Pathology;Hiroki Tokunaga 等;《arXiv:2007.08044v1》;全文 * |
一种结合GAN和伪标签的深度半监督模型研究;杨灿;;中国科技信息(17);全文 * |
基于ResNet 的音频场景声替换造假的检测算法;严迪群 等;《计算机应用》;全文 * |
基于伪标签半监督核局部Fisher判别分析轴承故障诊断;陶新民;任超;徐朗;何庆;刘锐;邹俊荣;;振动与冲击(17);全文 * |
基于可信标签扩展传递的跨领域倾向性分析;侯秀艳;刘培玉;孟凡龙;;计算机应用研究(05);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN115482418A (zh) | 2022-12-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115482418B (zh) | 基于伪负标签的半监督模型训练方法、系统及应用 | |
CN110347839A (zh) | 一种基于生成式多任务学习模型的文本分类方法 | |
US11288324B2 (en) | Chart question answering | |
CN112668579A (zh) | 基于自适应亲和力和类别分配的弱监督语义分割方法 | |
CN111738169B (zh) | 一种基于端对端网络模型的手写公式识别方法 | |
CN112148831B (zh) | 图文混合检索方法、装置、存储介质、计算机设备 | |
CN113378938B (zh) | 一种基于边Transformer图神经网络的小样本图像分类方法及系统 | |
CN112507912B (zh) | 一种识别违规图片的方法及装置 | |
CN112597324A (zh) | 一种基于相关滤波的图像哈希索引构建方法、系统及设备 | |
CN114612767B (zh) | 一种基于场景图的图像理解与表达方法、系统与存储介质 | |
CN112364747B (zh) | 一种有限样本下的目标检测方法 | |
CN111325237A (zh) | 一种基于注意力交互机制的图像识别方法 | |
CN111582506A (zh) | 基于全局和局部标记关系的偏多标记学习方法 | |
CN116486419A (zh) | 一种基于孪生卷积神经网络的书法字识别方法 | |
CN115393631A (zh) | 基于贝叶斯层图卷积神经网络的高光谱图像分类方法 | |
CN114998647B (zh) | 基于注意力多实例学习的乳腺癌全尺寸病理图像分类方法 | |
CN118468061B (zh) | 一种算法自动匹配及参数优化方法及系统 | |
CN115457332A (zh) | 基于图卷积神经网络和类激活映射的图像多标签分类方法 | |
CN111709442A (zh) | 一种面向图像分类任务的多层字典学习方法 | |
CN113240033B (zh) | 一种基于场景图高阶语义结构的视觉关系检测方法及装置 | |
Qin | Application of efficient recognition algorithm based on deep neural network in English teaching scene | |
CN117975464A (zh) | 基于U-Net的电气二次图纸文字信息的识别方法及系统 | |
CN117788917A (zh) | 基于伪标签的半监督酒店设施识别模型的训练方法、系统 | |
CN113535928A (zh) | 基于注意力机制下长短期记忆网络的服务发现方法及系统 | |
CN105787045A (zh) | 一种用于可视媒体语义索引的精度增强方法 |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20240205 Address after: 518000 1002, Building A, Zhiyun Industrial Park, No. 13, Huaxing Road, Henglang Community, Longhua District, Shenzhen, Guangdong Province Applicant after: Shenzhen Wanzhida Technology Co.,Ltd. Country or region after: China Address before: 315000 Fenghua Road, Jiangbei District, Ningbo, Zhejiang Province, No. 818 Applicant before: Ningbo University Country or region before: China |
|
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20240520 Address after: 219, 2nd Floor, Teaching Building Section II (Science and Technology Park Building A), West Campus of Beijing University of Chemical Technology, No. 98 Zizhuyuan Road, Haidian District, Beijing, 100000 Applicant after: CENTRAN TECHNOLOGY Co.,Ltd. Country or region after: China Address before: 518000 1002, Building A, Zhiyun Industrial Park, No. 13, Huaxing Road, Henglang Community, Longhua District, Shenzhen, Guangdong Province Applicant before: Shenzhen Wanzhida Technology Co.,Ltd. Country or region before: China |
|
GR01 | Patent grant |