{"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/harmonizing-base-and-novel-classes-a-class","title":"Harmonizing Base and Novel Classes: A Class-Contrastive Approach for Generalized Few-Shot Segmentation","arxiv_id":"2303.13724","date":"2023-03-24","proceeding":null,"authors":["Weide Liu","Zhonghua Wu","Yang Zhao","Yuming Fang","Chuan-Sheng Foo","Jun Cheng","Guosheng Lin"],"abstract":"Current methods for few-shot segmentation (FSSeg) have mainly focused on improving the performance of novel classes while neglecting the performance of base classes. To overcome this limitation, the task of generalized few-shot semantic segmentation (GFSSeg) has been introduced, aiming to predict segmentation masks for both base and novel classes. However, the current prototype-based methods do not explicitly consider the relationship between base and novel classes when updating prototypes, leading to a limited performance in identifying true categories. To address this challenge, we propose a class contrastive loss and a class relationship loss to regulate prototype updates and encourage a large distance between prototypes from different classes, thus distinguishing the classes from each other while maintaining the performance of the base classes. Our proposed approach achieves new state-of-the-art performance for the generalized few-shot segmentation task on PASCAL VOC and MS COCO datasets.","url_abs":"https://arxiv.org/abs/2303.13724v1","url_pdf":"https://arxiv.org/pdf/2303.13724v1.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":"harmonizing-base-and-novel-classes-a-class","repo_url":"https://github.com/liuweide01/HBNC","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-image-segmentation","task_name":"Few-Shot Semantic Segmentation"},{"task_slug":"generalized-few-shot-semantic-segmentation","task_name":"Generalized Few-Shot Semantic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/generalized-few-shot-semantic-segmentation-on-2","task":"Generalized Few-Shot Semantic Segmentation","dataset":"COCO-20i (1-shot)","model":"CCA (ResNet-50)","rank_in_archive_order":5,"of":6,"metrics":{"Mean Base and Novel":"27.86","Mean IoU":"37.48"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.13724","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}