AI Paper Atlas

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

Salvaging the Overlooked: Leveraging Class-Aware Contrastive Learning for Multi-Class Anomaly Detection

Lei Fan, Junjie Huang, Donglin Di, Anyang Su, Tianyou Song, Maurice Pagnucco, Yang Song

ICCV 2025 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 14 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
add local CL (ablation)RD (multi-class baseline) · MVTec+VISA+BTAD (all-in-all)I-AUROC/P-AUROC/PRO: +5.5/+2.1/+2.4Improved
add global CL (ablation)RD (multi-class baseline) · MVTec+VISA+BTAD (all-in-all)I-AUROC/P-AUROC/PRO: +4.2/+1.6/+2.0Improved
combine local and global CL (full CCL, raw class labels) (ablation)RD (multi-class baseline) · MVTec+VISA+BTAD (all-in-all)I-AUROC/P-AUROC/PRO: +5.7/+2.2/+2.8Improved
use K-means pseudo-class labels (K_C=30) instead of raw class labels (ablation)CCL · MVTec+VISA+BTAD (all-in-all)I-AUROC/P-AUROC/PRO: +5.7/+2.2/+2.8No clear effect
use pseudo-classes with K_C=60 instead of 30 (ablation)CCL · MVTec+VISA+BTAD (all-in-all)I-AUROC/P-AUROC/PRO: +5.0/+2.0/+2.2Hurt
add more feature scales to local CL (f3 -> {f2,f3} -> {f1,f2,f3}) (ablation)RD + local CL · MVTec+VISA+BTAD (all-in-all)I-AUROC: +2.9 -> +3.7 -> +5.1Improved
use 2-layer MLP projector instead of 4 conv blocks (ablation)RD + local CL · MVTec+VISA+BTAD (all-in-all)I-AUROC/P-AUROC/PRO: -15.3 / -8.9 / -23.8Hurt
use 4 conv blocks projector instead of 2 (ablation)RD + local CL · MVTec+VISA+BTAD (all-in-all)I-AUROC: +4.7 -> +5.1Improved
shrink local window k from max(h,w) to 1 (ablation)RD + local CL · MVTec+VISA+BTAD (all-in-all)I-AUROC: +5.1 -> +5.5Improved
replace triplet loss with L_gcl as global loss (ablation)RD + global CL · MVTec+VISA+BTAD (all-in-all)I-AUROC: 91.0 -> 95.2Improved
use all same-class samples as positives (L_gcl) instead of InfoNCE (ablation)RD + global CL · MVTec+VISA+BTAD (all-in-all)I-AUROC: 93.9 -> 95.2Improved
vary lambda1:lambda2 ratio (0.2 to 2) in CCL (ablation)CCL · MVTec+VISA+BTAD (all-in-all)I-AUROC: 96.7 (1:1) vs 96.5 (2)No clear effect

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