{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/learning-orthogonal-prototypes-for","title":"Learning Orthogonal Prototypes for Generalized Few-Shot Semantic Segmentation","arxiv_id":null,"date":"2023-01-01","proceeding":"CVPR 2023 1","authors":["Sun-Ao Liu","Yiheng Zhang","Zhaofan Qiu","Hongtao Xie","Yongdong Zhang","Ting Yao"],"abstract":"    Generalized few-shot semantic segmentation (GFSS) distinguishes pixels of base and novel classes from the background simultaneously, conditioning on sufficient data of base classes and a few examples from novel class. A typical GFSS approach has two training phases: base class learning and novel class updating. Nevertheless, such a stand-alone updating process often compromises the well-learnt features and results in performance drop on base classes. In this paper, we propose a new idea of leveraging Projection onto Orthogonal Prototypes (POP), which updates features to identify novel classes without compromising base classes. POP builds a set of orthogonal prototypes, each of which represents a semantic class, and makes the prediction for each class separately based on the features projected onto its prototype. Technically, POP first learns prototypes on base data, and then extends the prototype set to novel classes. The orthogonal constraint of POP encourages the orthogonality between the learnt prototypes and thus mitigates the influence on base class features when generalizing to novel prototypes. Moreover, we capitalize on the residual of feature projection as the background representation to dynamically fit semantic shifting (i.e., background no longer includes the pixels of novel classes in updating phase). Extensive experiments on two benchmarks demonstrate that our POP achieves superior performances on novel classes without sacrificing much accuracy on base classes. Notably, POP outperforms the state-of-the-art fine-tuning by 3.93% overall mIoU on PASCAL-5i in 5-shot scenario.    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2023/html/Liu_Learning_Orthogonal_Prototypes_for_Generalized_Few-Shot_Semantic_Segmentation_CVPR_2023_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2023/papers/Liu_Learning_Orthogonal_Prototypes_for_Generalized_Few-Shot_Semantic_Segmentation_CVPR_2023_paper.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":"learning-orthogonal-prototypes-for","repo_url":"https://github.com/lsa1997/POP","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"generalized-few-shot-semantic-segmentation","task_name":"Generalized Few-Shot 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":"POP(ResNet-50)","rank_in_archive_order":2,"of":6,"metrics":{"Mean Base and Novel":"35.01","Mean IoU":"44.98"},"uses_additional_data":false},{"leaderboard":"/sota/generalized-few-shot-semantic-segmentation-on-3","task":"Generalized Few-Shot Semantic Segmentation","dataset":"COCO-20i (5-shot)","model":"POP(ResNet-50)","rank_in_archive_order":2,"of":5,"metrics":{"Mean Base and Novel":"42.44","Mean IoU":"48.75"},"uses_additional_data":false},{"leaderboard":"/sota/generalized-few-shot-semantic-segmentation-on","task":"Generalized Few-Shot Semantic Segmentation","dataset":"PASCAL-5i (1-Shot)","model":"POP(ResNet-50)","rank_in_archive_order":3,"of":5,"metrics":{"Mean Base and Novel":"54.72","Mean IoU":"64.77"},"uses_additional_data":false},{"leaderboard":"/sota/generalized-few-shot-semantic-segmentation-on-1","task":"Generalized Few-Shot Semantic Segmentation","dataset":"PASCAL-5i (5-Shot)","model":"POP(ResNet-50)","rank_in_archive_order":2,"of":6,"metrics":{"Mean Base and Novel":"65.33","Mean IoU":"70.28"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"lsa1997/POP","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"5ea4deb0b3c0e576184f4339e14c9bb12ee66a678b8de071a9ca1469b23d4918","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}