{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mask-aware-iou-for-anchor-assignment-in-real","title":"Mask-aware IoU for Anchor Assignment in Real-time Instance Segmentation","arxiv_id":"2110.09734","date":"2021-10-19","proceeding":null,"authors":["Kemal Oksuz","Baris Can Cam","Fehmi Kahraman","Zeynep Sonat Baltaci","Sinan Kalkan","Emre Akbas"],"abstract":"This paper presents Mask-aware Intersection-over-Union (maIoU) for assigning anchor boxes as positives and negatives during training of instance segmentation methods. Unlike conventional IoU or its variants, which only considers the proximity of two boxes; maIoU consistently measures the proximity of an anchor box with not only a ground truth box but also its associated ground truth mask. Thus, additionally considering the mask, which, in fact, represents the shape of the object, maIoU enables a more accurate supervision during training. We present the effectiveness of maIoU on a state-of-the-art (SOTA) assigner, ATSS, by replacing IoU operation by our maIoU and training YOLACT, a SOTA real-time instance segmentation method. Using ATSS with maIoU consistently outperforms (i) ATSS with IoU by $\\sim 1$ mask AP, (ii) baseline YOLACT with fixed IoU threshold assigner by $\\sim 2$ mask AP over different image sizes and (iii) decreases the inference time by $25 \\%$ owing to using less anchors. Then, exploiting this efficiency, we devise maYOLACT, a faster and $+6$ AP more accurate detector than YOLACT. Our best model achieves $37.7$ mask AP at $25$ fps on COCO test-dev establishing a new state-of-the-art for real-time instance segmentation. Code is available at https://github.com/kemaloksuz/Mask-aware-IoU","url_abs":"https://arxiv.org/abs/2110.09734v1","url_pdf":"https://arxiv.org/pdf/2110.09734v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mask-aware-iou-for-anchor-assignment-in-real","repo_url":"https://github.com/kemaloksuz/mask-aware-iou","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"real-time-instance-segmentation","task_name":"Real-time Instance Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"atss","method_name":"ATSS"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/real-time-instance-segmentation-on-mscoco","task":"Real-time Instance Segmentation","dataset":"MSCOCO","model":"maYOLACT-700 (ResNet-50)","rank_in_archive_order":8,"of":22,"metrics":{"AP50":"59.4","AP75":"39.9","APL":"52.5","APM":"40.8","APS":"18.1","Frame (fps)":"25 (Tesla V100)","mask AP":"37.7"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-instance-segmentation-on-mscoco","task":"Real-time Instance Segmentation","dataset":"MSCOCO","model":"maYOLACT-550 (ResNet-50)","rank_in_archive_order":12,"of":22,"metrics":{"AP50":"56.2","AP75":"37.1","APL":"51.4","APM":"38.0","APS":"14.7","Frame (fps)":"30 (Tesla V100)","mask AP":"35.2"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2110.09734","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}