{"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/prototype-mixture-models-for-few-shot","title":"Prototype Mixture Models for Few-shot Semantic Segmentation","arxiv_id":"2008.03898","date":"2020-08-10","proceeding":"ECCV 2020 8","authors":["Boyu Yang","Chang Liu","Bohao Li","Jianbin Jiao","Qixiang Ye"],"abstract":"Few-shot segmentation is challenging because objects within the support and query images could significantly differ in appearance and pose. Using a single prototype acquired directly from the support image to segment the query image causes semantic ambiguity. In this paper, we propose prototype mixture models (PMMs), which correlate diverse image regions with multiple prototypes to enforce the prototype-based semantic representation. Estimated by an Expectation-Maximization algorithm, PMMs incorporate rich channel-wised and spatial semantics from limited support images. Utilized as representations as well as classifiers, PMMs fully leverage the semantics to activate objects in the query image while depressing background regions in a duplex manner. Extensive experiments on Pascal VOC and MS-COCO datasets show that PMMs significantly improve upon state-of-the-arts. Particularly, PMMs improve 5-shot segmentation performance on MS-COCO by up to 5.82\\% with only a moderate cost for model size and inference speed.","url_abs":"https://arxiv.org/abs/2008.03898v2","url_pdf":"https://arxiv.org/pdf/2008.03898v2.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":"prototype-mixture-models-for-few-shot","repo_url":"https://github.com/Yang-Bob/PMMs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"few-shot-image-segmentation","task_name":"Few-Shot Semantic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i-1","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i (1-shot)","model":"RPMM (ResNet-50)","rank_in_archive_order":81,"of":85,"metrics":{"Mean IoU":"30.6"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i-10","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i (10-shot)","model":"RPMM","rank_in_archive_order":4,"of":4,"metrics":{"Mean IoU":"33.1"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i-5","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i (5-shot)","model":"RPMM (ResNet-50)","rank_in_archive_order":78,"of":81,"metrics":{"Mean IoU":"35.5"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i -> Pascal VOC (1-shot)","model":"RPMM","rank_in_archive_order":13,"of":13,"metrics":{"Mean IoU":"49.6"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i-2","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i -> Pascal VOC (5-shot)","model":"RPMM","rank_in_archive_order":12,"of":12,"metrics":{"Mean IoU":"53.8"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-pascal-5i-1","task":"Few-Shot Semantic Segmentation","dataset":"PASCAL-5i (1-Shot)","model":"RPMM (ResNet-50)","rank_in_archive_order":96,"of":105,"metrics":{"Mean IoU":"56.3"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-pascal-5i","task":"Few-Shot Semantic Segmentation","dataset":"PASCAL-5i (10-Shot)","model":"RPMM","rank_in_archive_order":4,"of":4,"metrics":{"Mean IoU":"57.6"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-pascal-5i-5","task":"Few-Shot Semantic Segmentation","dataset":"PASCAL-5i (5-Shot)","model":"RPMM (ResNet-50)","rank_in_archive_order":92,"of":96,"metrics":{"Mean IoU":"57.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2008.03898","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}