AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

VisualAD: Language-Free Zero-Shot Anomaly Detection via Vision Transformer

Yanning Hou, Peiyuan Li, Zirui Liu, Yitong Wang, Yanran Ruan, Jianfeng Qiu, Ke Xu

CVPR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 7 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 SCA module (ablation)VisualAD (CLIP) · VisA (image-level)AUROC: 82.3 -> 84.7Improved
add SAF module (ablation)VisualAD (CLIP) · VisA (image-level)AUROC: 50.5 -> 84.7Improved
add SAF module (ablation)VisualAD (CLIP) · VisA (pixel-level)AP: 3.5 -> 28.4Improved
add both SCA and SAF (ablation)VisualAD (CLIP) · VisA (image-level)AUROC: 48.0 -> 84.7Improved
add focal loss (ablation)VisualAD (CLIP) · VisA (image-level)AUROC: 83.5 -> 84.7Improved
add dice loss (ablation)VisualAD (CLIP) · VisA (image-level)AUROC: 83.4 -> 84.7Improved
add token contrastive loss (ablation)VisualAD (CLIP) · VisA (image-level)AUROC: 84.2 -> 84.7Improved
increase anchors from 4 to 16 (ablation)VisualAD (CLIP) · VisA (image-level)AUROC: 84.7 -> 84.9No clear effect
increase anchors from 4 to 8 (ablation)VisualAD (CLIP) · VisA (pixel-level)AUROC: 95.8 -> 95.0Hurt
use all four layers instead of only layer 18 (ablation)VisualAD (CLIP) · VisA (image-level)AUROC: 82.4 -> 84.7Improved
add layer 24 to layers {6,12,18} (ablation)VisualAD (CLIP) · VisA (image-level)AUROC: 83.4 -> 84.7Improved
add positional encoding in SCA (ablation)VisualAD (CLIP) · VisA (pixel-level)AUROC: 93.0 -> 95.8Improved

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