UCoL: Unsupervised Learning of Discriminative Facial Representations via Uncertainty-Aware Contrast
Hao Wang, Min Li, Yangyang Song, Youjian Zhang, Liying Chi
Abstract
This paper presents Uncertainty-aware Contrastive Learning (UCoL): a fully unsupervised framework for discriminative facial representation learning. Our UCoL is built upon a momentum contrastive network, referred to as Dual-path Momentum Network. Specifically, two flows of pairwise contrastive training are conducted simultaneously: one is formed with intra-instance self augmentation, and the other is to identify positive pairs collected by online pairwise prediction. We introduce a novel uncertainty-aware consistency K-nearest neighbors algorithm to generate predicted positive pairs, which enables efficient discriminative learning from large-scale open-world unlabeled data. Experiments show that UCoL significantly improves the baselines of unsupervised models and performs on par with the semi-supervised and supervised face representation learning methods.
BibTeX
@article{Wang_Li_Song_Zhang_Chi_2023, title={UCoL: Unsupervised Learning of Discriminative Facial Representations via Uncertainty-Aware Contrast}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/25348}, DOI={10.1609/aaai.v37i2.25348}, abstractNote={This paper presents Uncertainty-aware Contrastive Learning (UCoL): a fully unsupervised framework for discriminative facial representation learning. Our UCoL is built upon a momentum contrastive network, referred to as Dual-path Momentum Network. Specifically, two flows of pairwise contrastive training are conducted simultaneously: one is formed with intra-instance self augmentation, and the other is to identify positive pairs collected by online pairwise prediction. We introduce a novel uncertainty-aware consistency K-nearest neighbors algorithm to generate predicted positive pairs, which enables efficient discriminative learning from large-scale open-world unlabeled data. Experiments show that UCoL significantly improves the baselines of unsupervised models and performs on par with the semi-supervised and supervised face representation learning methods.}, number={2}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Wang, Hao and Li, Min and Song, Yangyang and Zhang, Youjian and Chi, Liying}, year={2023}, month={Jun.}, pages={2510-2518} }