AI Paper Atlas

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

Reverse Engineering Self-Supervised Learning

Ido Ben-Shaul, Ravid Shwartz-Ziv, Tomer Galanti, Shai Dekel, Yann LeCun

NeurIPS 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Data-efficient and robust self-supervision · 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
larger regularization coefficient mu (25 instead of 5) in VICReg (ablation)VICReg RES-5-250 · CIFAR-100 linear probinglinear test accuracyImproved
increase regularization coefficient mu from 25 to 100 (ablation)VICReg RES-5-250 · CIFAR-100 linear probinglinear test accuracyNo clear effect
SSL (VICReg) versus supervised trainingRES-10-250 · CIFAR-100 NCC test accuracyNCC test accuracyNo clear effect
add data augmentation to supervised trainingsupervised RES-10-250 · CIFAR-100 NCC accuracyNCC test accuracyImproved
VICReg instead of SimCLRRES-5-250 · CIFAR-100 intermediate-layer linear accuracylinear test accuracyImproved
wider network (width 50, 250, 1000) (ablation)RES-5 VICReg · CIFAR-100 linear probinglinear test accuracyImproved
deeper network (RES-10-250 vs RES-5-250) (ablation)VICReg · CIFAR-100 linear probinglinear test accuracyMixed

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