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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add MSTFF multi-strategy text feature fusion (ablation) | AnomalyCLIP base · MVTec AD (image-level) | AUROC: 67.1 -> 82.0 | Improved |
| add MSTFF multi-strategy text feature fusion (ablation) | AnomalyCLIP base · MVTec AD (pixel-level) | PRO: 32.9 -> 68.0 | Improved |
| add MVFBE foreground-background enhancement (ablation) | FB-CLIP (with MSTFF) · MVTec AD | image AUROC / pixel PRO: 82.0 -> 92.2 AUROC; 68.0 -> 84.5 PRO | Improved |
| add SCR alone to base (ablation) | AnomalyCLIP base · MVTec AD | image AUROC / pixel PRO: AUROC 67.1 -> 65.4; PRO 32.9 -> 45.5 | Mixed |
| add SCR alone to base (ablation) | AnomalyCLIP base · VisA | image AUROC: 45.7 -> 63.8 | Improved |
| add BS and SCR on top of MSTFF+MVFBE (full model) (ablation) | FB-CLIP · VisA | image AUROC: 88.4 -> 89.5 | Improved |
| FB-CLIP versus AF-CLIP | zero-shot AD · BTAD and TN3K | AUROC: BTAD 94.3 -> 93.2; TN3K 80.5 -> 79.0 (pixel) | Mixed |
Closest papers by meaning
- Proximity-CLIP: Text-Guided Semantic Proximity Learning for Zero-Shot Anomaly Detection (ECCV 2026 · similarity 0.90)
- AA-CLIP: Enhancing Zero-Shot Anomaly Detection via Anomaly-Aware CLIP (CVPR 2025 · similarity 0.89)
- DLVP-CLIP: Enhancing Fine-Grained Zero-Shot Anomaly Detection via Dynamic Local Visual Prompting (CVPR 2026 · similarity 0.89)
- FG-CLIP: Fine-Grained Visual and Textual Alignment (ICML 2025 · similarity 0.88)
- Aligning and Prompting Anything for Zero-Shot Generalized Anomaly Detection (AAAI 2025 · similarity 0.87)
- AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection (ICLR 2024 · similarity 0.86)
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.
