AI Paper Atlas

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

ResAD++: Towards Class Agnostic Anomaly Detection via Residual Feature Learning

Xincheng Yao, Chao Shi, Muming Zhao, Guangtao Zhai, C L Zhang

IJCV 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 2 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 residual features instead of initial features (ablation)ResAD++ · MVTecADkurtosis: 0.261 -> 1.679Improved
use residual features instead of initial features (ablation)ResAD++ · VisAkurtosis: 0.757 -> 1.313Improved
add feature hypersphere constraining to residual features (ablation)ResAD++ · MVTecADfeature scale std across classes: 0.147 -> 0.005Improved
add feature hypersphere constraining to residual features (ablation)ResAD++ · VisAfeature scale std across classes: 0.098 -> 0.004Improved
use ImageBind instead of WideResNet50 as feature extractor (ablation)ResAD++ · Average over 8 AD datasets, 2-shotimage-level AUROC: 78.1 -> 82.1Improved
use ImageBind instead of WideResNet50 as feature extractor (ablation)ResAD++ · Kvasir-Seg, 8-shotimage-level AUROC: 90.5 -> 83.4Hurt
increase reference shots from 2 to 8ResAD++ (W50) · Average over 8 AD datasetsimage-level AUROC: 78.1 -> 83.7Improved
increase reference shots from 2 to 8ResAD++ (ImageBind) · Average over 8 AD datasetspixel-level AUROC: 91.2 -> 92.1Improved
add log-barrier contraction, VQ matching and new loss over ResAD (ImageBind)ResAD++ · Average over 8 AD datasets, 2-shotimage-level AUROC: 79.6 -> 82.1Improved
add log-barrier contraction, VQ matching and new loss over ResAD (ImageBind)ResAD++ · Average over 8 AD datasets, 8-shotPRO: 80.0 -> 80.9Improved

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