most citedSymmetric Neural-Collapse Representations with Supervised Contrastive Loss: The Impact of ReLU and Batching

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

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2023

Engineering the Neural Collapse Geometry of Supervised-Contrastive Loss

Jaidev Gill, Vala Vakilian, Christos Thrampoulidis

Supervised-contrastive loss (SCL) is an alternative to cross-entropy (CE) for classification tasks that makes use of similarities in the embedding space to allow for richer represe…

cs.LG2023★ 1 cited

Symmetric Neural-Collapse Representations with Supervised Contrastive Loss: The Impact of ReLU and Batching

Ganesh Ramachandra Kini, Vala Vakilian, Tina Behnia +2

Supervised contrastive loss (SCL) is a competitive and often superior alternative to the cross-entropy loss for classification. While prior studies have demonstrated that both loss…