AI Paper Atlas

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

Learning to Augment Distributions for Out-of-distribution Detection

Qizhou Wang, Zhen Fang, Yonggang Zhang, Feng Liu, Yixuan Li, Bo Han

NeurIPS 2023 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based OOD detection · 8 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
DAL (distributional augmentation) vs conventional outlier exposureOE · CIFAR-10 averageFPR95: 4.67 -> 2.68Improved
DAL vs conventional outlier exposureOE · CIFAR-10 averageAUROC: 98.88 -> 99.01Improved
DAL vs conventional outlier exposureOE · CIFAR-100 averageFPR95: 43.14 -> 29.68Improved
DAL vs conventional outlier exposureOE · CIFAR-100 averageAUROC: 90.27 -> 93.92Improved
DAL vs ATOM sampling strategyATOM · CIFAR-100 averageFPR95: 37.84 -> 29.68Improved
DAL vs POEMPOEM · CIFAR-100 averageFPR95: 34.77 -> 29.68Improved
DAL vs POEMPOEM · CIFAR-10 averageFPR95: 2.81 -> 2.68No clear effect
DAL vs DOE (worst-case OOD learning)DOE · CIFAR-100 averageFPR95: 40.95 -> 29.68Improved
use auxiliary OOD data (OE) instead of ID data onlyMSP · CIFAR-10 averageFPR95: 50.15 -> 4.67Improved
DAL vs OE on hard OODOE · CIFAR-10 vs CIFAR-100FPR95: 29.40 -> 25.45Improved
DAL vs POEM on LSUN-FixPOEM · CIFAR-10 vs LSUN-FixFPR95: 1.24 -> 1.39Hurt
large Wasserstein radius rho=100 with large perturbation strength ps=10 (ablation)DAL · CIFAR-100FPR95Hurt

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