Skip to content
conftrace_

bayesian data augmentation

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

gradient bia (1) negative sample (1) vision-language representation (1) self-supervised learning (1) contrastive learning (1) representation learning (1) stochastic optimization (1)

Papers

Why do We Need Large Batchsizes in Contrastive Learning? A Gradient-Bias Perspective NeurIPS 2022