AI Paper Atlas

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

Leverage Your Local and Global Representations: A New Self-Supervised Learning Strategy

CVPR 2022 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Data-efficient and robust self-supervision · 24 citations (OpenAlex)

Check 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
Add local-to-local dissimilarity to LoGo (ablation)MoCo-LoGo · CIFAR10KNN accuracy (%): 82.31 -> 84.44Helped
Add local-to-local dissimilarity to LoGo (ablation)MoCo-LoGo · STL10KNN accuracy (%): 74.26 -> 76.79Helped
Add local-to-local dissimilarity to LoGo (ablation)MoCo-LoGo · ImageNet-100KNN accuracy (%): 69.00 -> 76.82Helped
Add local-to-local dissimilarity to LoGo (ablation)SimSiam-LoGo · CIFAR10KNN accuracy (%): 83.33 -> 87.67Helped
Add local-to-local dissimilarity to LoGo (ablation)SimSiam-LoGo · STL10KNN accuracy (%): 60.21 -> 76.96Helped
Add local-to-local dissimilarity to LoGo (ablation)SimSiam-LoGo · ImageNet-100KNN accuracy (%): 76.64 -> 78.48Helped
Replace the learned local-crop affinity with cosine distance (ablation)LoGo · TrainingKNN accuracyHurt

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