AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

Bypassing the Transport Plan: Dynamic Reweighting for Out-of-Distribution Detection with Optimal Transport

Yang Xiao, Weiming Liu, Jun Dan, Tengyue Xu, Fan Wang, Hua Yu, Junhao Dong, Jiao Liu, Shunjie Dong, Lianyong Qi

CVPR 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection

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
replace max-softmax OOD scoring with DREW-supervised OOD head (ablation)Fixmatch · CIFAR-100 (55 known, 50 labels/class)AUROC: 57.3 -> 91.7Improved
replace POT redundant-mass OT with dynamic reweighting (ablation)FixMatch+POT · CIFAR-100 (55 known, 50 labels/class)AUROC: 88.4 -> 91.7Improved
replace POT with DREW on CIFAR-10 AUROCPOT · CIFAR-10 (6 known classes)AUROC: 99.7 -> 99.6 (50 labels/class)No clear effect
use exact EMD solver instead of Sinkhorn in DREW (ablation)DREW · CIFAR-100 (55 known, 50 labels/class)AUROC: 91.2 -> 91.5Improved
plug DREW into any OT solver vs POT (ablation)POT · CIFAR-100 (55 known, 50 labels/class)AUROC: 90.1 -> 91.0Improved
remove need for redundant mass k (DREW vs POT with k=1.25) (ablation)POT · CIFAR-100 (55 known, 50 labels/class)pseudo-label AUROC: 54.9 -> 59.7Improved
vary tau_a from 0.001 to 1 (ablation)DREW · CIFAR-100accuracy/AUROCNo clear effect
set OOD loss weight gamma too small (0.01) (ablation)DREW · CIFAR-100OOD detection qualityHurt
DREW vs POT on ImageNet-30POT · ImageNet-30 (20 known classes)AUROC: 97.4 -> 97.6No clear effect
approximate SemiUOT with smooth log-sum-exp for training speedDREW · Training efficiencys/iterationImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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