Hierarchical Proxy-Based Loss for Deep Metric Learning

Zhibo Yang, Muhammet Bastan, Xinliang Zhu, Douglas Gray, Dimitris Samaras; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022, pp. 1859-1868

Abstract


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 real-world 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.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2022_WACV, author = {Yang, Zhibo and Bastan, Muhammet and Zhu, Xinliang and Gray, Douglas and Samaras, Dimitris}, title = {Hierarchical Proxy-Based Loss for Deep Metric Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2022}, pages = {1859-1868} }