AI Paper Atlas

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

FB-CLIP: Fine-Grained Zero-Shot Anomaly Detection with Foreground-Background Disentanglement

Ming Hu, Yongsheng Huo, Mingyu Dou, Jianfu Yin, Peng Zhao, Yao Wang, Cong Hu, Bingliang Hu, Quan Wang

CVPR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 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
add MSTFF multi-strategy text feature fusion (ablation)AnomalyCLIP base · MVTec AD (image-level)AUROC: 67.1 -> 82.0Improved
add MSTFF multi-strategy text feature fusion (ablation)AnomalyCLIP base · MVTec AD (pixel-level)PRO: 32.9 -> 68.0Improved
add MVFBE foreground-background enhancement (ablation)FB-CLIP (with MSTFF) · MVTec ADimage AUROC / pixel PRO: 82.0 -> 92.2 AUROC; 68.0 -> 84.5 PROImproved
add SCR alone to base (ablation)AnomalyCLIP base · MVTec ADimage AUROC / pixel PRO: AUROC 67.1 -> 65.4; PRO 32.9 -> 45.5Mixed
add SCR alone to base (ablation)AnomalyCLIP base · VisAimage AUROC: 45.7 -> 63.8Improved
add BS and SCR on top of MSTFF+MVFBE (full model) (ablation)FB-CLIP · VisAimage AUROC: 88.4 -> 89.5Improved
FB-CLIP versus AF-CLIPzero-shot AD · BTAD and TN3KAUROC: BTAD 94.3 -> 93.2; TN3K 80.5 -> 79.0 (pixel)Mixed

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