Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2604.08301 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915927444946944 |
|---|---|
| author | Liu, Yishen Chen, Hongcang Zhao, Pengcheng Bao, Yunfan Tian, Yuxi Zhang, Jieming Chen, Hao Zhi, Zheng Liu, Yongchun Li, Ying Cao, Dongpu |
| author_facet | Liu, Yishen Chen, Hongcang Zhao, Pengcheng Bao, Yunfan Tian, Yuxi Zhang, Jieming Chen, Hao Zhi, Zheng Liu, Yongchun Li, Ying Cao, Dongpu |
| contents | The performance of visual anomaly inspection in industrial quality control is often constrained by the scarcity of real anomalous samples. Consequently, anomaly synthesis techniques have been developed to enlarge training sets and enhance downstream inspection. However, existing methods either suffer from poor integration caused by inpainting or fail to provide accurate masks. To address these limitations, we propose GroundingAnomaly, a novel few-shot anomaly image generation framework. Our framework introduces a Spatial Conditioning Module that leverages per-pixel semantic maps to enable precise spatial control over the synthesized anomalies. Furthermore, a Gated Self-Attention Module is designed to inject conditioning tokens into a frozen U-Net via gated attention layers. This carefully preserves pretrained priors while ensuring stable few-shot adaptation. Extensive evaluations on the MVTec AD and VisA datasets demonstrate that GroundingAnomaly generates high-quality anomalies and achieves state-of-the-art performance across multiple downstream tasks, including anomaly detection, segmentation, and instance-level detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_08301 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GroundingAnomaly: Spatially-Grounded Diffusion for Few-Shot Anomaly Synthesis Liu, Yishen Chen, Hongcang Zhao, Pengcheng Bao, Yunfan Tian, Yuxi Zhang, Jieming Chen, Hao Zhi, Zheng Liu, Yongchun Li, Ying Cao, Dongpu Computer Vision and Pattern Recognition The performance of visual anomaly inspection in industrial quality control is often constrained by the scarcity of real anomalous samples. Consequently, anomaly synthesis techniques have been developed to enlarge training sets and enhance downstream inspection. However, existing methods either suffer from poor integration caused by inpainting or fail to provide accurate masks. To address these limitations, we propose GroundingAnomaly, a novel few-shot anomaly image generation framework. Our framework introduces a Spatial Conditioning Module that leverages per-pixel semantic maps to enable precise spatial control over the synthesized anomalies. Furthermore, a Gated Self-Attention Module is designed to inject conditioning tokens into a frozen U-Net via gated attention layers. This carefully preserves pretrained priors while ensuring stable few-shot adaptation. Extensive evaluations on the MVTec AD and VisA datasets demonstrate that GroundingAnomaly generates high-quality anomalies and achieves state-of-the-art performance across multiple downstream tasks, including anomaly detection, segmentation, and instance-level detection. |
| title | GroundingAnomaly: Spatially-Grounded Diffusion for Few-Shot Anomaly Synthesis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.08301 |