期刊
2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022)
卷 -, 期 -, 页码 449-458出版社
IEEE COMPUTER SOC
DOI: 10.1109/WACV51458.2022.00052
关键词
-
类别
资金
- US National Science Foundation [IIS-1763981]
- Partner University Fund
- SUNY2020 Infrastructure Transportation Security Center
Proxy-based metric learning losses, by imposing hierarchical structure on the proxies, are able to capture both class-discriminative features and class-shared characteristics, thereby improving the performance of image retrieval, especially on large datasets with strong hierarchical structure.
Proxy-based metric learning losses are superior to pair-based losses due to their fast convergence and low training complexity. However, existing proxy-based losses focus on learning class-discriminative features while overlooking the commonalities shared across classes which are potentially useful in describing and matching samples. Moreover, they ignore the implicit hierarchy of categories in realworld datasets, where similar subordinate classes can be grouped together. In this paper, we present a framework that leverages this implicit hierarchy by imposing a hierarchical structure on the proxies and can be used with any existing proxy-based loss. This allows our model to capture both class-discriminative features and class-shared characteristics without breaking the implicit data hierarchy. We evaluate our method on five established image retrieval datasets such as In-Shop and SOP. Results demonstrate that our hierarchical proxy-based loss framework improves the performance of existing proxy-based losses, especially on large datasets which exhibit strong hierarchical structure.
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