Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908341511389184 |
|---|---|
| author | Jin, Ying Peng, Jinlong He, Qingdong Hu, Teng Wu, Jiafu Chen, Hao Wang, Haoxuan Zhu, Wenbing Chi, Mingmin Liu, Jun Wang, Yabiao |
| author_facet | Jin, Ying Peng, Jinlong He, Qingdong Hu, Teng Wu, Jiafu Chen, Hao Wang, Haoxuan Zhu, Wenbing Chi, Mingmin Liu, Jun Wang, Yabiao |
| contents | The performance of anomaly inspection in industrial manufacturing is constrained by the scarcity of anomaly data. To overcome this challenge, researchers have started employing anomaly generation approaches to augment the anomaly dataset. However, existing anomaly generation methods suffer from limited diversity in the generated anomalies and struggle to achieve a seamless blending of this anomaly with the original image. Moreover, the generated mask is usually not aligned with the generated anomaly. In this paper, we overcome these challenges from a new perspective, simultaneously generating a pair of the overall image and the corresponding anomaly part. We propose DualAnoDiff, a novel diffusion-based few-shot anomaly image generation model, which can generate diverse and realistic anomaly images by using a dual-interrelated diffusion model, where one of them is employed to generate the whole image while the other one generates the anomaly part. Moreover, we extract background and shape information to mitigate the distortion and blurriness phenomenon in few-shot image generation. Extensive experiments demonstrate the superiority of our proposed model over state-of-the-art methods in terms of diversity, realism and the accuracy of mask. Overall, our approach significantly improves the performance of downstream anomaly inspection tasks, including anomaly detection, anomaly localization, and anomaly classification tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_13509 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation Jin, Ying Peng, Jinlong He, Qingdong Hu, Teng Wu, Jiafu Chen, Hao Wang, Haoxuan Zhu, Wenbing Chi, Mingmin Liu, Jun Wang, Yabiao Computer Vision and Pattern Recognition The performance of anomaly inspection in industrial manufacturing is constrained by the scarcity of anomaly data. To overcome this challenge, researchers have started employing anomaly generation approaches to augment the anomaly dataset. However, existing anomaly generation methods suffer from limited diversity in the generated anomalies and struggle to achieve a seamless blending of this anomaly with the original image. Moreover, the generated mask is usually not aligned with the generated anomaly. In this paper, we overcome these challenges from a new perspective, simultaneously generating a pair of the overall image and the corresponding anomaly part. We propose DualAnoDiff, a novel diffusion-based few-shot anomaly image generation model, which can generate diverse and realistic anomaly images by using a dual-interrelated diffusion model, where one of them is employed to generate the whole image while the other one generates the anomaly part. Moreover, we extract background and shape information to mitigate the distortion and blurriness phenomenon in few-shot image generation. Extensive experiments demonstrate the superiority of our proposed model over state-of-the-art methods in terms of diversity, realism and the accuracy of mask. Overall, our approach significantly improves the performance of downstream anomaly inspection tasks, including anomaly detection, anomaly localization, and anomaly classification tasks. |
| title | Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.13509 |