AI Paper Atlas

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

A Closer Look at Benchmarking Self-supervised Pre-training with Image Classification

Markus Marks, Manuel Knott, Neehar Kondapaneni, Elijah Cole, Thijs Defraeye, Fernando Pérez‐Cruz, Pietro Perona

IJCV 2025 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Data-efficient and robust self-supervision · 22 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
add batch norm before the linear classifier (ablation)MaskFeat ViT-B/16 linear probing · ImageNet-1ktop-1 accuracy: 3.7 -> 51.7Improved
add z-score normalization to kNN probing (ablation)MAE ViT-B/16 · ImageNet-1ktop-1 accuracy: 26.6 -> 47.7Improved
add z-score normalization to kNN probing (ablation)DINO ViT-B/16 · ImageNet-1ktop-1 accuracy: 74.7 -> 74.9No clear effect
add final batch norm to 10% fine-tuning (ablation)DINO ViT-B/16 · ImageNet-1k 10% labelstop-1 accuracy: 75.4 -> 76.6Improved
add final batch norm to 1% fine-tuning (ablation)DINO ViT-B/16 · ImageNet-1k 1% labelstop-1 accuracy: 65.6 -> 69.2Improved
switch backbone from ResNet-50 to ViT-B/16 (ablation)DINO · ImageNet-1k fine-tuningtop-1 accuracy: 76.0 -> 81.3Improved
switch backbone from ResNet-50 to ViT-B/16 (ablation)MoCo v3 · ImageNet-1k fine-tuningtop-1 accuracy: 76.2 -> 80.8Improved
use linear probing instead of full fine-tuning as in-domain predictor of OOD ranking (ablation)26 SSL models · OOD average (11 datasets)Spearman r: 0.85 vs 0.79Improved
use in-domain probing instead of fine-tuning to predict OOD kNN ranking under categorical shift (ablation)26 SSL models · categorical shiftSpearman r: 0.96 vs 0.62Improved
use style shift instead of categorical shift for OOD fine-tuning ranking (ablation)26 SSL models · OOD FTSpearman r: 0.73 -> 0.61Hurt
use 10% fine-tuning as predictor of OOD fine-tuning (ablation)26 SSL models · OOD FTSpearman rImproved
use ResNet to ViT backbone for generative vs discriminative comparison (ablation)SSL families · ImageNetfine-tune vs linear probe gapImproved

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