AI Paper Atlas

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

DisCoPatch: Taming Adversarially-driven Batch Statistics for Improved Out-of-Distribution Detection

Francisco Caetano, Christiaan Viviers, Luis A. Zavala-Mondragón, Peter H.N. De With, Fons van der Sommen

ICCV 2025 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 5 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
use test-batch statistics in BatchNorm instead of learned running statistics (BS=64) (ablation)DisCoPatch · Near-OODAUROC: 38.4 -> 99.3Improved
use test-batch statistics in BatchNorm instead of learned running statistics (BS=64) (ablation)DisCoPatch · Far-OODAUROC: 34.5 -> 96.1Improved
increase batch size of test batch from 1 to 256 (ablation)DisCoPatch · Near-OODAUROC: 64.9 -> 100.0Improved
increase batch size of test batch from 1 to 256 (ablation)DisCoPatch · Far-OODAUROC: 70.9 -> 98.1Improved
use BatchNorm instead of GroupNorm (ablation)DisCoPatch-64 · Covariate ShiftAUROC: 78.5 -> 97.2Improved
use BatchNorm instead of InstanceNorm (ablation)DisCoPatch-64 · Covariate ShiftAUROC: 86.2 -> 97.2Improved
use BatchNorm instead of InstanceNorm (ablation)DisCoPatch-64 · Near-OODAUROC: 92.8 -> 95.1Improved
use BatchNorm instead of GroupNorm (ablation)DisCoPatch-64 · Far-OODAUROC: 81.0 -> 96.6Improved
increase patches per image from 4 to 64 (ablation)DisCoPatch · Near-OODAUROC: 90.3 -> 95.1Improved
increase patches per image from 4 to 64 (ablation)DisCoPatch · Far-OODAUROC: 92.6 -> 96.6Improved
increase patches per image from 64 to 512 (ablation)DisCoPatch · Near-OODAUROC: 95.1 -> 95.3No clear effect
increase patches per image from 4 to 64 (ablation)DisCoPatch · Covariate ShiftAUROC: 93.0 -> 97.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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