Proceedings

Free Lunch of Image-mask Alignment for Anomaly Image Generation and Segmentation

Xiangyue Li, Xiaoyang Wang, Zhibin Wan, Quan Zhang, Yupei Wu, Tao Deng, Mingjie Sun

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 1449-1457.

https://doi.org/10.24963/ijcai.2025/162

Keywords

  • Computer Vision: CV: Segmentation, grouping and shape analysis

Abstract

This paper aims at generating anomalous images and their segmentation labels to address the lack of real-world anomaly samples and privacy issues. Departing from conventional approaches that use masks solely to guide the generation of anomaly images, we propose a dual-branch training strategy for the generative model. This strategy enables the simultaneous production of anomaly images and masks, with an alignment regularization loss that ensures the coherence between the generated images and their masks. During inference, only the image-generation branch is activated to produce synthetic samples for training the downstream segmentation model. Furthermore, we propose to integrate the well-trained generative model into the training of segmentation models, utilizing a generative feedback loss to refine the segmentation model's performance. Experiments show our method's IoU metrics exceed previous methods by 5.03%, 5.68% and 16.63% on Real-IAD (industrial), polyp (medical), and Floor Dirty (indoor) datasets. The code is publicly accessible at https://github.com/huan-yin/anomaly-alignment.

Xiangyue Li, Xiaoyang Wang, Zhibin Wan, Quan Zhang, Yupei Wu, Tao Deng, and Mingjie Sun. 2025. Free Lunch of Image-mask Alignment for Anomaly Image Generation and Segmentation. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 1449–1457. https://doi.org/10.24963/ijcai.2025/162
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards