SSVP: Synergistic Semantic-Visual Prompting for Industrial Zero-Shot Anomaly Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915737570902016 |
|---|---|
| author | Fu, Chenhao Fang, Han Zheng, Xiuzheng Wei, Wenbo Li, Yonghua Sun, Hao Li, Xuelong |
| author_facet | Fu, Chenhao Fang, Han Zheng, Xiuzheng Wei, Wenbo Li, Yonghua Sun, Hao Li, Xuelong |
| contents | Zero-Shot Anomaly Detection (ZSAD) leverages Vision-Language Models (VLMs) to enable supervision-free industrial inspection. However, existing ZSAD paradigms are constrained by single visual backbones, which struggle to balance global semantic generalization with fine-grained structural discriminability. To bridge this gap, we propose Synergistic Semantic-Visual Prompting (SSVP), that efficiently fuses diverse visual encodings to elevate model's fine-grained perception. Specifically, SSVP introduces the Hierarchical Semantic-Visual Synergy (HSVS) mechanism, which deeply integrates DINOv3's multi-scale structural priors into the CLIP semantic space. Subsequently, the Vision-Conditioned Prompt Generator (VCPG) employs cross-modal attention to guide dynamic prompt generation, enabling linguistic queries to precisely anchor to specific anomaly patterns. Furthermore, to address the discrepancy between global scoring and local evidence, the Visual-Text Anomaly Mapper (VTAM) establishes a dual-gated calibration paradigm. Extensive evaluations on seven industrial benchmarks validate the robustness of our method; SSVP achieves state-of-the-art performance with 93.0% Image-AUROC and 92.2% Pixel-AUROC on MVTec-AD, significantly outperforming existing zero-shot approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_09147 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SSVP: Synergistic Semantic-Visual Prompting for Industrial Zero-Shot Anomaly Detection Fu, Chenhao Fang, Han Zheng, Xiuzheng Wei, Wenbo Li, Yonghua Sun, Hao Li, Xuelong Computer Vision and Pattern Recognition Artificial Intelligence Zero-Shot Anomaly Detection (ZSAD) leverages Vision-Language Models (VLMs) to enable supervision-free industrial inspection. However, existing ZSAD paradigms are constrained by single visual backbones, which struggle to balance global semantic generalization with fine-grained structural discriminability. To bridge this gap, we propose Synergistic Semantic-Visual Prompting (SSVP), that efficiently fuses diverse visual encodings to elevate model's fine-grained perception. Specifically, SSVP introduces the Hierarchical Semantic-Visual Synergy (HSVS) mechanism, which deeply integrates DINOv3's multi-scale structural priors into the CLIP semantic space. Subsequently, the Vision-Conditioned Prompt Generator (VCPG) employs cross-modal attention to guide dynamic prompt generation, enabling linguistic queries to precisely anchor to specific anomaly patterns. Furthermore, to address the discrepancy between global scoring and local evidence, the Visual-Text Anomaly Mapper (VTAM) establishes a dual-gated calibration paradigm. Extensive evaluations on seven industrial benchmarks validate the robustness of our method; SSVP achieves state-of-the-art performance with 93.0% Image-AUROC and 92.2% Pixel-AUROC on MVTec-AD, significantly outperforming existing zero-shot approaches. |
| title | SSVP: Synergistic Semantic-Visual Prompting for Industrial Zero-Shot Anomaly Detection |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2601.09147 |