期刊
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
卷 -, 期 -, 页码 9924-9933出版社
IEEE COMPUTER SOC
DOI: 10.1109/CVPR46437.2021.00980
关键词
-
资金
- National Natural Science Foundation of China [61922006]
- CAAI-Huawei MindSpore Open Fund
- Baidu academic collaboration program
The study proposes a novel cross-domain co-attention scheme for more accurate knowledge transfer through learning pixel-wise cross-domain correspondences.
Cross-domain weakly supervised object detection aims to adapt object-level knowledge from a fully labeled source domain dataset (i.e., with object bounding boxes) to train object detectors for target domains that are weakly labeled (i.e., with image-level tags). Instead of domain-level distribution matching, as popularly adopted in the literature, we propose to learn pixel-wise cross-domain correspondences for more precise knowledge transfer. It is realized through a novel cross-domain co-attention scheme trained as region competition. In this scheme, the cross-domain correspondence module seeks for informative features on the target domain image, which if warped to the source domain image, could best explain its annotations. Meanwhile, a collaborative mask generator competes to mask out the relevant target image region to make the remaining features uninformative. Such competitive learning strives to correlate the full foreground in cross-domain image pairs, revealing the accurate object extent in target domain. To alleviate the ambiguity of inter-domain correspondence learning, a domain-cycle consistency regularizer is further proposed to leverage the more reliable intra-domain correspondence. The proposed approach achieves consistent improvements over existing approaches by a considerable margin, demonstrated by the experiments on various datasets.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据