AI Paper Atlas

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

An Empirical Study of Training Self-Supervised Vision Transformers

Xinlei Chen, Saining Xie, Kaiming He

ICCV 2021 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Data-efficient and robust self-supervision · 1,947 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
freeze the patch projection layer (random patch projection) (ablation)MoCo v3 ViT-B/16 · ImageNet-1k linear probing (lr=1.5e-4)top-1 accuracy: +1.7% to 73.4%Improved
freeze the patch projection layer (random patch projection) (ablation)SimCLR ViT-B/16 · ImageNet-1k linear probingtop-1 accuracy: +0.8%Improved
freeze the patch projection layer (random patch projection) (ablation)BYOL ViT-B/16 · ImageNet-1k linear probingtop-1 accuracy: +1.3%Improved
freeze the patch projection layer (random patch projection) (ablation)SwAV ViT · ImageNet-1k linear probingtop-1 accuracy: 65.8% -> 66.4%Improved
increase batch size from 2k to 4k (ablation)MoCo v3 ViT-B/16 · ImageNet-1k linear probing (100-ep)top-1 accuracy: 72.6 -> 72.2Hurt
increase batch size from 4k to 6k (ablation)MoCo v3 ViT-B/16 · ImageNet-1k linear probing (100-ep)top-1 accuracy: 72.2 -> 69.7Hurt
increase base lr from 0.5e-4 to 1.0e-4 (ablation)MoCo v3 ViT-B/16 · ImageNet-1k linear probing (100-ep, batch 4096)top-1 accuracy: 70.4 -> 72.2Improved
add sin-cos position embedding (versus none) (ablation)MoCo v3 ViT-B · ImageNet-1k linear probing (300-ep)top-1 accuracy: 74.9 -> 76.5Improved
remove class token but keep the final LayerNorm (ablation)MoCo v3 ViT-B · ImageNet-1k linear probing (300-ep)top-1 accuracy: 76.5 -> 69.7Hurt
add BatchNorm in MLP heads (ablation)MoCo v3 ViT-B · ImageNet-1k linear probing (300-ep)top-1 accuracy: 74.4 -> 76.5Improved
add prediction MLP head (ablation)MoCo v3 ViT-B · ImageNet-1k linear probing (300-ep)top-1 accuracy: 75.5 -> 76.5Improved
add momentum encoder (m=0.99 instead of m=0) (ablation)MoCo v3 ViT-B · ImageNet-1k linear probing (300-ep)top-1 accuracy: 74.3 -> 76.5Improved

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