atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

A theoretical study of inductive biases in contrastive learning

ICLR 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Contrastive versus non-contrastive theory · 1 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Increase the requested partition size from m=10 to m=300ResNet-18 · CIFAR-10 testphi_m: 0.131 -> 0.521Hurt
Increase the requested partition size from m=10 to m=300ResNet-101 · CIFAR-10 testphi_m: 0.053 -> 0.459Hurt
Increase the requested partition size from m=10 to m=300WRN · CIFAR-10 testphi_m: 0.080 -> 0.340Hurt
Increase the requested partition size from m=10 to m=300ViT · CIFAR-10 testphi_m: 0.072 -> 0.389Hurt
Use ResNet-101 instead of ResNet-18CIFAR-10 contrastive model · CIFAR-10 test, m=10phi_m: 0.131 -> 0.053Helped
Use WRN instead of ResNet-18CIFAR-10 contrastive model · CIFAR-10 test, m=10phi_m: 0.131 -> 0.080Helped
Use ViT instead of ResNet-18CIFAR-10 contrastive model · CIFAR-10 test, m=10phi_m: 0.131 -> 0.072Helped

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy