Confidence-Aware Adversarial Learning for Self-supervised Semantic Matching

doi:10.1007/978-3-030-60633-6_8

	Confidence-Aware Adversarial Learning for Self-supervised Semantic Matching
	Huang, Shuaiyi; Wang, Qiuyue; He, Xuming
	2020
会议录名称	LECTURE NOTES IN COMPUTER SCIENCE
ISSN	0302-9743 ; 1611-3349
卷号	12305 LNCS
页码	91-103
DOI	10.1007/978-3-030-60633-6_8
摘要	In this paper, we aim to address the challenging task of semantic matching where matching ambiguity is difficult to resolve even with learned deep features. We tackle this problem by taking into account the confidence in predictions and develop a novel refinement strategy to correct partial matching errors. Specifically, we introduce a Confidence-Aware Semantic Matching Network (CAMNet) which instantiates two key ideas of our approach. First, we propose to estimate a dense confidence map for a matching prediction through self-supervised learning. Second, based on the estimated confidence, we refine initial predictions by propagating reliable matching to the rest of locations on the image plane. In addition, we develop a new hybrid loss in which we integrate a semantic alignment loss with a confidence loss, and an adversarial loss that measures the quality of semantic correspondence. We are the first that exploit confidence during refinement to improve semantic matching accuracy and develop an end-to-end self-supervised adversarial learning procedure for the entire matching network. We evaluate our method on two public benchmarks, on which we achieve top performance over the prior state of the art. We will release our source code at https://github.com/ShuaiyiHuang/CAMNet. © 2020, Springer Nature Switzerland AG.
会议录编者/会议主办者	Pattern Recognition and Computer Vision - 3rd Chinese Conference, PRCV 2020, Proceedings
关键词	Benchmarking Computer vision ForecastingAdversarial learning Matching networks Partial matching Refinement strategy Semantic alignments Semantic correspondence Semantic matching State of the art
会议名称	3rd Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2020
会议地点	Nanjing, China
会议日期	October 16, 2020 - October 18, 2020
URL	查看原文
收录类别	EI
语种	英语
出版者	Springer Science and Business Media Deutschland GmbH
EI入藏号	20204409410260
EI主题词	Semantics
原始文献类型	Conference article (CA)
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/124516
专题	信息科学与技术学院_PI研究组_何旭明组信息科学与技术学院_硕士生
通讯作者	He, Xuming
作者单位	ShanghaiTech University, Shanghai, China
第一作者单位	上海科技大学
通讯作者单位	上海科技大学
第一作者的第一单位	上海科技大学
推荐引用方式 GB/T 7714	Huang, Shuaiyi,Wang, Qiuyue,He, Xuming. Confidence-Aware Adversarial Learning for Self-supervised Semantic Matching[C]//Pattern Recognition and Computer Vision - 3rd Chinese Conference, PRCV 2020, Proceedings:Springer Science and Business Media Deutschland GmbH,2020:91-103.