AI Paper Atlas

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

Risk-Bounded Distribution Reconstruction: Stable Statistic Calibration for Long-Tailed Recognition

Guanliang Liu, Wenchao Chen, Long Tian, Xuefei Cao, Hongwei Liu, Bo Chen

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Decoupled and calibrated long-tail training

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
apply RBDR calibration instead of plain cross-entropy trainingtwo-stage classifier · CIFAR100-LT (imbalance 200)Top-1 accuracy: 34.80 -> 49.02Improved
use RBDR instead of FURfeature-space reconstruction · CIFAR100-LT (imbalance 200, 100)Top-1 accuracy: +2.82% at rho=200, +2.97% at rho=100Improved
use RBDR instead of FURfeature-space reconstruction · ImageNet-LTTop-1 accuracy (All): 55.50 -> 55.91Improved
use RBDR instead of FeatRecontwo-stage classifier · ImageNet-LTTop-1 accuracy (All): 57.80 -> 55.91Hurt
replace Gaussian covariance calibrator with class-conditional latent diffusion (RBDR-DDIM) (ablation)RBDR · ImageNet-LT and iNaturalist 2018Top-1 accuracy (All): 55.91 -> 55.32 (ImageNet-LT), 72.92 -> 72.35 (iNaturalist)Hurt
add supportive projection to OT initialization (ablation)RBDR · CIFAR100-LT (imbalance 100)Top-1 accuracy (All): 52.46 -> 53.42Improved
add low-rank shrinkage on top of supportive projection (ablation)RBDR · CIFAR100-LT (imbalance 100)Top-1 accuracy (All): 53.42 -> 53.87Improved
add supportive projection to OT initialization (ablation)RBDR · ImageNet-LTTop-1 accuracy (All): 53.23 -> 55.08Improved
add low-rank shrinkage on top of supportive projection (ablation)RBDR · ImageNet-LTTop-1 accuracy (All): 55.08 -> 55.91Improved
add supportive projection to OT initialization (ablation)RBDR · iNaturalist 2018Top-1 accuracy (All): 70.17 -> 72.28Improved
add low-rank shrinkage on top of supportive projection (ablation)RBDR · iNaturalist 2018Top-1 accuracy (All): 72.28 -> 72.92Improved
evaluate RBDR vs OT initialization on the 10 scarcest CIFAR100-LT classesRBDR · CIFAR100-LT (imbalance 100), 10 scarcest classesper-class accuracy: turtle 5.4% -> 14.6%; +4.7% on averageImproved

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