Background-Aware Classification Activation Map for Weakly Supervised Object Localization

Author:

Zhu Lei1ORCID,She Qi2ORCID,Chen Qian1ORCID,Meng Xiangxi3ORCID,Geng Mufeng1ORCID,Jin Lujia1ORCID,Zhang Yibao3ORCID,Ren Qiushi1ORCID,Lu Yanye1ORCID

Affiliation:

1. Institute of Medical Technology, Peking University Health Science Center, Peking University, Beijing, China

2. ByteDance AI Lab, ByteDance, Beijing, China

3. Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education), Peking University Cancer Hospital & Institute, Beijing, China

Funder

National Natural Science Foundation of China

Beijing Natural Science Foundation

Peking University Medicine Sailing Program for Young Scholars’ Scientific & Technological Innovation

Shenzhen Science and Technology Program, China

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Applied Mathematics,Artificial Intelligence,Computational Theory and Mathematics,Computer Vision and Pattern Recognition,Software

Reference67 articles.

1. Weakly supervised instance segmentation using the bounding box tightness prior;Hsu

2. Counterfactual contrastive learning for weakly-supervised vision-language grounding;Zhang

3. Self-Supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation

4. Learning Deep Features for Discriminative Localization

5. Weakly-Supervised Learning of Visual Relations

Cited by 6 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Weakly supervised learning based bone abnormality detection from musculoskeletal x-rays;Multimedia Tools and Applications;2024-06-28

2. PatchMix: patch-level mixup for data augmentation in convolutional neural networks;Knowledge and Information Systems;2024-05-30

3. Learning to Detour: Shortcut Mitigating Augmentation for Weakly Supervised Semantic Segmentation;2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV);2024-01-03

4. Adaptive Zone Learning for Weakly Supervised Object Localization;IEEE Transactions on Neural Networks and Learning Systems;2024

5. Understanding Convolutional Neural Networks From Excitations;IEEE Transactions on Neural Networks and Learning Systems;2024

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3