AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Does Weak-to-strong Generalization Happen under Spurious Correlations?

Chenruo Liu, Yijun Dong, Qi Lei

ICLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 1 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
retrain strong student on high-confidence subset with GCE loss after W2S fine-tuning (Enhanced-W2S)vanilla W2S · Waterbirds, BFFHQ, BG-COCO, ImageNet-9 average accuracyrelative accuracy improvement (%): +7.02 / +4.32 / +7.50 / +11.73 mean relative improvementImproved
add Enhanced-W2S to vanilla W2S on a few pairsvanilla W2S · BFFHQ and BG-COCO (eta_l=eta_o, eta_u=0.5)relative accuracy improvement (%): -1.37 (Clipb32/MAE BFFHQ); -3.52 (DINOv2/MAE BG-COCO)Hurt
add Enhanced-W2S for worst-group accuracyvanilla W2S · Waterbirds, BFFHQ, BG-COCO worst-group accuracyrelative worst-group improvement (%): +21.14 / +3.81 / +7.73Improved
use GCE loss instead of CE loss in retraining (ablation)Enhanced-W2S · Waterbirds (eta_l=0.5, eta_u=eta_o)average accuracy (x1e-2): +3.27 over CE variantImproved
use GCE loss instead of CE loss in retraining (ablation)Enhanced-W2S · ImageNet-9 (eta_l=eta_o, eta_u=0.5)average accuracy (x1e-2): +0.51 over CE variantImproved
use confidence-based high-confidence subset instead of all unlabeled data (ablation)Enhanced-W2S · Waterbirds (eta_l=eta_o, eta_u=0.5)average accuracy (x1e-2): +4.84 over p=1 variantImproved
use confidence-based subset instead of all unlabeled data (ablation)Enhanced-W2S · ImageNet-9 (eta_l=eta_o, eta_u=0.5)average accuracy (x1e-2): +5.08 over p=1 variantImproved
increase gap between unlabeled and labeled minority fractions (eta_u vs eta_l)vanilla W2S · four spurious-correlation benchmarksW2S gainHurt
raise minority share of unlabeled data when teacher is group-balanced (eta_l=0.5)vanilla W2S · four spurious-correlation benchmarksW2S gainImproved

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