AI Paper Atlas

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

Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning

Zixin Wen, Yuanzhi Li

ICML 2021 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Inductive bias and minimal representations · 11 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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
Use RandomMask to create disjoint positive viewsContrastive learning with a one-hidden-layer ReLU network · Sparse coding model, downstream classificationaccuracy: o(1) -> 1 - o(1)Improved
Remove data augmentation (ablation)Contrastive learning with a one-hidden-layer ReLU network · Sparse coding model, downstream classificationaccuracy: 1 - o(1) -> o(1)Hurt
Use crop-resize without color distortion (ablation)Contrastive learning on CIFAR10 · CIFAR10 representationsfeature sparsityHurt
Use standard augmentations including color distortionContrastive learning on CIFAR10 · CIFAR10 representationsfeature sparsityImproved

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