Mark Ibrahim

most citedOccam's Razor for Self Supervised Learning: What is Sufficient to Learn Good Representations?

1 citations · 1 across the 2 of their papers we have counts for

collaborators

Showing cs.CVShow all

1 paper · 1 filter

cs.CV2024

$X$ -Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs

Vlad Sobal, Mark Ibrahim, Randall Balestriero +5

Learning good representations involves capturing the diverse ways in which data samples relate. Contrastive loss - an objective matching related samples - underlies methods from se…

X-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs

$X$ -Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs