AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

SALAD -- Semantics-Aware Logical Anomaly Detection

Matic Fučka, Vitjan Zavrtanik, Danijel Skočaj

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Industrial 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 a discriminative composition branch trained on composition maps (ablation)SALAD · MVTec LOCOimage AUROC (logical): 93.0 -> 96.5Improved
add the appearance branch (ablation)SALAD · MVTec LOCOimage AUROC (structural): 91.2 -> 95.7Improved
add the global (stat) branch (ablation)SALAD · MVTec LOCOimage AUROC (avg): 94.2 -> 96.1Improved
use the three branches together instead of any single branch (ablation)SALAD · MVTec LOCOimage AUROC (avg): 85.4 -> 96.1 (composition only vs full)Improved
use class-wise global descriptor with spatially-grouped means instead of single global mean vector (ablation)SALAD global branch · MVTec LOCOimage AUROC (logical): 95.6 -> 96.5Improved
use EfficientAD features rather than ResNet50 for global representation (ablation)SALAD global branch · MVTec LOCOimage AUROC (avg): 92.7 -> 96.1Improved
use removal, inpainting and DRAEM synthetic anomalies together (ablation)composition branch · MVTec LOCOimage AUROC (avg): 95.2 -> 96.1 (without removal)Improved
swap appearance branch to TransFusion, DSR or DRAEM (ablation)SALAD · MVTec LOCOimage AUROC (avg): 96.1 -> 95.4 (TransFusion), 94.4 (DSR), 94.0 (DRAEM)Mixed
use DINOv2 instead of DINO for composition map generation (ablation)SALAD · MVTec LOCOimage AUROC (avg): 96.1 -> 95.5Hurt
increase number of clusters from 4 to 6 or 8 (ablation)composition map generation · MVTec LOCOimage AUROC (avg): 95.4 (K=4), 96.1 (K=6), 95.9 (K=8)No clear effect
train SALAD with supervised PSAD composition mapsSALAD · MVTec LOCOimage AUROC (avg): 96.1 -> 97.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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