785 citations · 1.4k across the 23 of their papers we have counts for
Showing 2021Show all
3 papers · 1 filter
cs.CV2021
Equivariant Contrastive Learning
Rumen Dangovski, Li Jing, Charlotte Loh +5
In state-of-the-art self-supervised learning (SSL) pre-training produces semantically good representations by encouraging them to be invariant under meaningful transformations pres…
cs.CV2021★ 92 cited
Understanding Dimensional Collapse in Contrastive Self-supervised Learning
Li Jing, Pascal Vincent, Yann LeCun +1
Self-supervised visual representation learning aims to learn useful representations without relying on human annotations. Joint embedding approach bases on maximizing the agreement…
cs.CV2021★ 785 cited
Barlow Twins: Self-Supervised Learning via Redundancy Reduction
Jure Zbontar, Li Jing, Ishan Misra +2
Self-supervised learning (SSL) is rapidly closing the gap with supervised methods on large computer vision benchmarks. A successful approach to SSL is to learn embeddings which are…