{"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/part-aware-prototype-network-for-few-shot","title":"Part-aware Prototype Network for Few-shot Semantic Segmentation","arxiv_id":"2007.06309","date":"2020-07-13","proceeding":"ECCV 2020 8","authors":["Yongfei Liu","Xiangyi Zhang","Songyang Zhang","Xuming He"],"abstract":"Few-shot semantic segmentation aims to learn to segment new object classes with only a few annotated examples, which has a wide range of real-world applications. Most existing methods either focus on the restrictive setting of one-way few-shot segmentation or suffer from incomplete coverage of object regions. In this paper, we propose a novel few-shot semantic segmentation framework based on the prototype representation. Our key idea is to decompose the holistic class representation into a set of part-aware prototypes, capable of capturing diverse and fine-grained object features. In addition, we propose to leverage unlabeled data to enrich our part-aware prototypes, resulting in better modeling of intra-class variations of semantic objects. We develop a novel graph neural network model to generate and enhance the proposed part-aware prototypes based on labeled and unlabeled images. Extensive experimental evaluations on two benchmarks show that our method outperforms the prior art with a sizable margin.","url_abs":"https://arxiv.org/abs/2007.06309v3","url_pdf":"https://arxiv.org/pdf/2007.06309v3.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":"part-aware-prototype-network-for-few-shot","repo_url":"https://github.com/Xiangyi1996/PPNet-PyTorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"part-aware-prototype-network-for-few-shot","repo_url":"https://github.com/LiheYoung/MiningFSS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-image-segmentation","task_name":"Few-Shot Semantic Segmentation"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"object","task_name":"Object"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-semantic-segmentation","task_name":"Semi-Supervised Semantic Segmentation"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"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":"PPNet (ResNet-50)","rank_in_archive_order":82,"of":85,"metrics":{"Mean IoU":"29.0","learnable parameters (million)":"31.5"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i-2-1","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i (2-way 1-shot)","model":"PPNet (ResNet-50)","rank_in_archive_order":5,"of":6,"metrics":{"mIoU":"20.4"},"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":"PPNet (ResNet-50)","rank_in_archive_order":74,"of":81,"metrics":{"Mean IoU":"38.5","learnable parameters (million)":"31.5"},"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":"PPNet (ResNet-50)","rank_in_archive_order":102,"of":105,"metrics":{"Mean IoU":"51.5","learnable parameters (million)":"31.5"},"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":"PPNet (ResNet-50)","rank_in_archive_order":82,"of":96,"metrics":{"Mean IoU":"62.0","learnable parameters (million)":"31.5"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-pascal5i-1","task":"Few-Shot Semantic Segmentation","dataset":"Pascal5i","model":"PPNet","rank_in_archive_order":3,"of":3,"metrics":{"meanIOU":"55.16"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.06309","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}