AI Paper Atlas

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

Delving Deep into Simplicity Bias for Long-Tailed Image Recognition

Xiu-Shen Wei, Xuhao Sun, Yang Shen, Peng Wang

IJCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Decoupled and calibrated long-tail training · 5 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 holistic-level SSL to the CE baseline (ablation)CE baseline · ImageNet-LTAll accuracy: 52.5 -> 55.8Improved
add partial-level SSL to the CE baseline (ablation)CE baseline · ImageNet-LTAll accuracy: 52.5 -> 55.2Improved
add partial-level SSL on top of holistic-level SSL (ablation)CE + H-SSL · ImageNet-LTAll accuracy: 55.8 -> 57.0Improved
add augmented-level SSL on top of holistic and partial levels (ablation)CE + H-SSL + P-SSL · ImageNet-LTAll accuracy: 57.0 -> 59.1Improved
add augmented-level SSL on top of holistic and partial levels (ablation)CE + H-SSL + P-SSL · ImageNet-LT (Few)Few accuracy: 35.7 -> 38.3Improved
use all queue examples of predicted class c' instead of a single example (ablation)3LSSL augmented queue · ImageNet-LTAll accuracy: 57.8 -> 59.1Improved
use predicted class c' rather than ground-truth class c for the augmented queue (ablation)3LSSL augmented queue · ImageNet-LTAll accuracy: 58.9 -> 59.1Improved
use predicted class c' rather than ground-truth class c for the augmented queue (ablation)3LSSL augmented queue · ImageNet-LT (Few)Few accuracy: 37.8 -> 38.3Improved
increase partial-level masking stages from 1 to 3 (ablation)3LSSL partial-level SSL · ImageNet-LTAll accuracy: 59.1 -> 58.7Hurt
increase partial-level masking stages from 1 to 2 (ablation)3LSSL partial-level SSL · ImageNet-LTAll accuracy: 59.1 -> 59.0No clear effect
add MoCo-v2 SSL to CE pre-trainingCE (frozen backbone, classifier re-trained) · Long-tailed CIFAR-100 (IF 100)Tail accuracy: 45.36 -> 48.20Improved
use SSL alone instead of CE for pre-trainingfrozen backbone, classifier re-trained · Long-tailed CIFAR-100 (IF 100)All accuracy: 55.50 -> 28.89Hurt

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