{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T22:23:12Z","timestamp":1772317392410,"version":"3.50.1"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9]]},"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.24963\/ijcai.2025\/162","type":"proceedings-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:10:40Z","timestamp":1758269440000},"page":"1449-1457","source":"Crossref","is-referenced-by-count":1,"title":["Free Lunch of Image-mask Alignment for Anomaly Image Generation and Segmentation"],"prefix":"10.24963","author":[{"given":"Xiangyue","family":"Li","sequence":"first","affiliation":[{"name":"Soochow University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Xi\u2019an Jiaotong-Liverpool University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhibin","family":"Wan","sequence":"additional","affiliation":[{"name":"Soochow University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xi\u2019an Jiaotong-Liverpool University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yupei","family":"Wu","sequence":"additional","affiliation":[{"name":"Aqrose Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Deng","sequence":"additional","affiliation":[{"name":"Soochow University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingjie","family":"Sun","sequence":"additional","affiliation":[{"name":"Soochow University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"name":"Thirty-Fourth International Joint Conference on Artificial Intelligence {IJCAI-25}","theme":"Artificial Intelligence","location":"Montreal, Canada","acronym":"IJCAI-2025","number":"34","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2025,8,16]]},"end":{"date-parts":[[2025,8,22]]}},"container-title":["Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T11:33:10Z","timestamp":1758627190000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2025\/162"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2025\/162","relation":{},"subject":[],"published":{"date-parts":[[2025,9]]}}}