{"type":"ScholarlyArticle","title":"Free Lunch of Image-mask Alignment for Anomaly Image Generation and Segmentation","authors":[{"name":"Xiangyue Li","slug":"xiangyue-li","given":"Xiangyue","family":"Li","affiliation":""},{"name":"Xiaoyang Wang","slug":"xiaoyang-wang","given":"Xiaoyang","family":"Wang","affiliation":""},{"name":"Zhibin Wan","slug":"zhibin-wan","given":"Zhibin","family":"Wan","affiliation":""},{"name":"Quan Zhang","slug":"quan-zhang","given":"Quan","family":"Zhang","affiliation":""},{"name":"Yupei Wu","slug":"yupei-wu","given":"Yupei","family":"Wu","affiliation":""},{"name":"Tao Deng","slug":"tao-deng","given":"Tao","family":"Deng","affiliation":""},{"name":"Mingjie Sun","slug":"mingjie-sun","given":"Mingjie","family":"Sun","affiliation":""}],"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.","doi":"10.24963/ijcai.2025/162","url":"https://ijcai.org/proceedings/2025/162","pdf":"https://ijcai.org/proceedings/2025/0162.pdf","markdown":"https://ijcai.org/proceedings/2025/162.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/162","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Computer Vision","track":"Main Track","number":162,"pages":{"first":1449,"last":1457},"keywords":["Computer Vision: CV: Segmentation, grouping and shape analysis"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}