{"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/long-tailed-instance-segmentation-using","title":"Long-tailed Instance Segmentation using Gumbel Optimized Loss","arxiv_id":"2207.10936","date":"2022-07-22","proceeding":null,"authors":["Konstantinos Panagiotis Alexandridis","Jiankang Deng","Anh Nguyen","Shan Luo"],"abstract":"Major advancements have been made in the field of object detection and segmentation recently. However, when it comes to rare categories, the state-of-the-art methods fail to detect them, resulting in a significant performance gap between rare and frequent categories. In this paper, we identify that Sigmoid or Softmax functions used in deep detectors are a major reason for low performance and are sub-optimal for long-tailed detection and segmentation. To address this, we develop a Gumbel Optimized Loss (GOL), for long-tailed detection and segmentation. It aligns with the Gumbel distribution of rare classes in imbalanced datasets, considering the fact that most classes in long-tailed detection have low expected probability. The proposed GOL significantly outperforms the best state-of-the-art method by 1.1% on AP , and boosts the overall segmentation by 9.0% and detection by 8.0%, particularly improving detection of rare classes by 20.3%, compared to Mask-RCNN, on LVIS dataset. Code available at: https://github.com/kostas1515/GOL","url_abs":"https://arxiv.org/abs/2207.10936v2","url_pdf":"https://arxiv.org/pdf/2207.10936v2.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":"long-tailed-instance-segmentation-using","repo_url":"https://github.com/kostas1515/gol","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":"object-detection","task_name":"Object Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"gumbel-activation","method_name":"Gumbel Activation"}],"datasets_introduced":[],"methods_introduced":[{"slug":"gumbel-activation","name":"Gumbel Activation","full_name":"Gumbel Cross Entropy"}],"results":[{"leaderboard":"/sota/instance-segmentation-on-lvis-v1-0-val","task":"Instance Segmentation","dataset":"LVIS v1.0 val","model":"R101-FPN-MaskRCNN-GOL","rank_in_archive_order":17,"of":25,"metrics":{"mask AP":"29.0"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-lvis-v1-0-val","task":"Instance Segmentation","dataset":"LVIS v1.0 val","model":"R50-FPN-MaskRCNN-GOL","rank_in_archive_order":20,"of":25,"metrics":{"mask AP":"27.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.10936","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}