Stars
SSL
5 repositories
speech self-supervised representations
Weakly Supervised End-to-End Learning (NeurIPS 2021)
[ECCV2022] New benchmark for evaluating pre-trained model; New supervised contrastive learning framework.
(Hybrid) BYOL-S feature extractor using serab-byols package in pytorch.
[CVPR 2022] Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization