期刊
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
卷 -, 期 -, 页码 11396-11405出版社
IEEE
DOI: 10.1109/ICCV48922.2021.01122
关键词
-
资金
- National Key R&D Program of China [2018YFB1402605]
- National Natural Science Foundation of China [61822208, 62021001]
- Youth Innovation Promotion Association CAS [2018497]
- GPU cluster built by MCC Lab of Information Science and Technology Institution, USTC
A novel deep local feature learning architecture is proposed to focus on multiple discriminative local patterns in an image. The framework utilizes dynamic attention and metric learning to train the architecture, achieving efficient retrieval performance.
In image retrieval, learning local features with deep convolutional networks has been demonstrated effective to improve the performance. To discriminate deep local features, some research efforts turn to attention learning. However, existing attention-based methods only generate a single attention map for each image, which limits the exploration of diverse visual patterns. To this end, we propose a novel deep local feature learning architecture to simultaneously focus on multiple discriminative local patterns in an image. In our framework, we first adaptively reorganize the channels of activation maps for multiple heads. For each head, a new dynamic attention module is designed to learn the potential attentions. The whole architecture is trained as metric learning of weighted-sum-pooled global image features, with only image-level relevance label. After the architecture training, for each database image, we select local features based on their multi-head dynamic attentions, which are further indexed for efficient retrieval. Extensive experiments show the proposed method outperforms the state-ofthe-art methods on the Revisited Oxford and Paris datasets. Besides, it typically achieves competitive results even using local features with lower dimensions. Code will be released at https://github.com/CHANWH/MDA.
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