DomainFeat: Learning Local Features With Domain Adaptation
文献类型:期刊论文
作者 | Xu, Rongtao3,4; Wang, Changwei3,4; Xu, Shibiao3; Meng, Weiliang3,4; Zhang, Yuyang2; Fan, Bin1; Zhang, Xiaopeng3,4 |
刊名 | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY |
出版日期 | 2024 |
卷号 | 34期号:1页码:46-59 |
ISSN号 | 1051-8215 |
关键词 | Feature extraction Location awareness Visualization Robustness Image matching Detectors Decoding Local features domain adaptation cross-domain data consistency loss |
DOI | 10.1109/TCSVT.2023.3282956 |
通讯作者 | Xu, Shibiao(shibiaoxu@bupt.edu.cn) |
英文摘要 | Accurate and efficient keypoint detection and description is a fundamental step in various computer vision tasks. In this paper, we extract robust descriptors and detect accurate keypoints by learning local Features with Domain adaptation (DomainFeat). Specifically, our Domainfeat includes image-level domain invariance supervision, pixel-level domain consistency supervision, Pixel-Adaptive keypoint Detection(PA-Det), and cross-domain dataset with domain stable point supervision. First, we introduce the image-level domain invariance supervision to make the high-level feature distributions from different domains close by fusing domain-invariant representations in the decoder. Furthermore, to compensate for the inconsistency between descriptors corresponding to the keypoints at the pixel level, we propose the pixel-level domain consistency supervision. Then we present the Pixel-Adaptive keypoint Detection to efficiently detect accurate keypoints, which can improve accuracy by enhancing the local consistency of heatmaps. Finally, we propose an efficient approach to construct data and supervision labels in diverse domains, which can tackle complex application scenarios. With these novel modules and supervision methods, our DomainFeat can make feature detectors more accurate and descriptors more robust. Extensive experiments confirm that Domainfeat achieves state-of-the-art performance on benchmarks such as Aachen-Day-Night localization, HPatches image matching, and the challenging DNIM dataset. |
资助项目 | National Natural Science Foundation of China |
WOS研究方向 | Engineering |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:001138814400010 |
资助机构 | National Natural Science Foundation of China |
源URL | [http://ir.ia.ac.cn/handle/173211/55536] |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Xu, Shibiao |
作者单位 | 1.Univ Sci & Technol Beijing, Sch Intelligence Sci & Technol, Beijing 100083, Peoples R China 2.Thunder Software Technol Co Ltd, Chengdu 610000, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China 4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
推荐引用方式 GB/T 7714 | Xu, Rongtao,Wang, Changwei,Xu, Shibiao,et al. DomainFeat: Learning Local Features With Domain Adaptation[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2024,34(1):46-59. |
APA | Xu, Rongtao.,Wang, Changwei.,Xu, Shibiao.,Meng, Weiliang.,Zhang, Yuyang.,...&Zhang, Xiaopeng.(2024).DomainFeat: Learning Local Features With Domain Adaptation.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,34(1),46-59. |
MLA | Xu, Rongtao,et al."DomainFeat: Learning Local Features With Domain Adaptation".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 34.1(2024):46-59. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。