UCoL: Unsupervised Learning of Discriminative Facial Representations via Uncertainty-Aware Contrast

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.

Cite

Text

Wang et al. "UCoL: Unsupervised Learning of Discriminative Facial Representations via Uncertainty-Aware Contrast." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I2.25348

Markdown

[Wang et al. "UCoL: Unsupervised Learning of Discriminative Facial Representations via Uncertainty-Aware Contrast." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/wang2023aaai-ucol/) doi:10.1609/AAAI.V37I2.25348

BibTeX

@inproceedings{wang2023aaai-ucol,
  title     = {{UCoL: Unsupervised Learning of Discriminative Facial Representations via Uncertainty-Aware Contrast}},
  author    = {Wang, Hao and Li, Min and Song, Yangyang and Zhang, Youjian and Chi, Liying},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {2510-2518},
  doi       = {10.1609/AAAI.V37I2.25348},
  url       = {https://mlanthology.org/aaai/2023/wang2023aaai-ucol/}
}