AI Paper Atlas

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

Rethinking Long-tailed Dataset Distillation: A Uni-Level Framework with Unbiased Recovery and Relabeling

Xiao Cui, Yulei Qin, Xinyue Li, Wengang Zhou, Hongsheng Li, Houqiang Li

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Classifier rebalancing and margin losses · 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
add model debiasing (mixture consistency + class-wise debias loss) (ablation)Ours · CIFAR-100-LT (IF=50, IPC=10)accuracy (%): 31.7 -> 42.1Improved
add fair BN statistics recalibration (ablation)Ours · CIFAR-100-LT (IF=50, IPC=10)accuracy (%): 40.9 -> 42.1Improved
add confidence-guided multi-round initialization (ablation)Ours · CIFAR-100-LT (IF=50, IPC=10)accuracy (%): 40.8 -> 42.1Improved
replace bi-level trajectory matching (DAMED) with uni-level BN statistic alignmentOurs · CIFAR-100-LT (IF=10, IPC=10)accuracy (%): 31.5 -> 47.1Improved
replace DAMED with ours on Tiny-ImageNet-LTOurs · Tiny-ImageNet-LT (IF=10, IPC=10)accuracy (%): 26.0 -> 37.8Improved
replace DAMED with ours under extreme imbalance IF=256 with ResNet-50Ours · ImageNet-LT (IF=256, IPC=10)accuracy (%): 17.2 -> 48.2Improved
replace DAMED with ours at IPC=1Ours · CIFAR-10-LT (IF=100, IPC=1)accuracy (%): 24.1 -> 44.8Improved
use ours vs DAMED peak memoryOurs · CIFAR-100-LTpeak GPU memory (GB): 10.2 -> 3.1 (IPC=10)Improved

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