AI Paper Atlas

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

Confusion-Aware Spectral Regularizer for Long-Tailed Recognition

Ziquan Zhu, Gaojie Jin, Hanruo Zhu, Si-Yuan Lu, Yunxiao Zhang, Zeyu Fu, Ronghui Mu, Guoqiang Zhang, Zhao Sun, Yuhang Xia, Jiaxing Shang, Xiang Li and 2 more

CVPR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Decoupled and calibrated long-tail training · 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
remove frequency-aware class weight Lambda (ablation)CAR · ImageNet-LT (from scratch)overall accuracy: 54.39 -> 57.48 (with Lambda)Improved
remove frequency-aware class weight Lambda (ablation)CAR · CIFAR100-LT (from scratch)overall accuracy: 49.62 -> 51.85 (with Lambda)Improved
add EMA confusion estimator (ablation)CAR · ImageNet-LT (from scratch)overall accuracy: 55.77 -> 57.48Improved
add EMA confusion estimator (ablation)CAR · CIFAR100-LT (from scratch)overall accuracy: 50.20 -> 51.85Improved
add CAR regularizer to cross-entropy trainingViT-Small · ImageNet-LT (from scratch)overall accuracy: 46.51 -> 57.48Improved
combine CAR with ConCutMixCAR · ImageNet-LT (from scratch)overall accuracy: 57.48 -> 60.07Improved
add CAR to long-tailed augmentation methods (ReMix, MetaSAug, CMO, SAFA, ConCutMix)CAR · ImageNet-LT / CIFAR100-LT, IF 50/100/200overall accuracy: e.g. 57.48 -> 60.07 (ImageNet-LT IF=100 + ConCutMix)Improved
CAR vs LOS on worst-class test accuracyLOS · ImageNet-LTworst-class test accuracy: 10 -> 18Improved
CAR vs LOS under pre-trained ViT-SmallLOS · iNaturalist (pretrained)overall accuracy: 83.02 -> 83.74Improved
CAR vs best baseline head accuracyLOS · ImageNet-LT (from scratch)head accuracy: 70.79 -> 67.00Hurt
CAR across backbones ViT-Tiny/Base/Large, ResNet, Swinbest baseline · ImageNet-LTtop-1 accuracy: ViT-Large 68.63 -> 69.26Improved

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