-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2022_CVPR, author = {Zhang, Shu and Xu, Ran and Xiong, Caiming and Ramaiah, Chetan}, title = {Use All the Labels: A Hierarchical Multi-Label Contrastive Learning Framework}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {16660-16669} }
Use All the Labels: A Hierarchical Multi-Label Contrastive Learning Framework
Abstract
Current contrastive learning frameworks focus on leveraging a single supervisory signal to learn representations, which limits the efficacy on unseen data and downstream tasks. In this paper, we present a hierarchical multi-label representation learning framework that can leverage all available labels and preserve the hierarchical relationship between classes. We introduce novel hierarchy preserving losses, which jointly apply a hierarchical penalty to the contrastive loss, and enforce the hierarchy constraint. The loss function is data driven and automatically adapts to arbitrary multi-label structures. Experiments on several datasets show that our relationship-preserving embedding performs well on a variety of tasks and outperform the baseline supervised and self-supervised approaches. Code is available at https://github.com/salesforce/hierarchicalContrastiveLearning.
Related Material