{"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/a-few-guidelines-for-incremental-few-shot","title":"Prototype-based Incremental Few-Shot Semantic Segmentation","arxiv_id":"2012.01415","date":"2020-11-30","proceeding":null,"authors":["Fabio Cermelli","Massimiliano Mancini","Yongqin Xian","Zeynep Akata","Barbara Caputo"],"abstract":"Semantic segmentation models have two fundamental weaknesses: i) they require large training sets with costly pixel-level annotations, and ii) they have a static output space, constrained to the classes of the training set. Toward addressing both problems, we introduce a new task, Incremental Few-Shot Segmentation (iFSS). The goal of iFSS is to extend a pretrained segmentation model with new classes from few annotated images and without access to old training data. To overcome the limitations of existing models iniFSS, we propose Prototype-based Incremental Few-Shot Segmentation (PIFS) that couples prototype learning and knowledge distillation. PIFS exploits prototypes to initialize the classifiers of new classes, fine-tuning the network to refine its features representation. We design a prototype-based distillation loss on the scores of both old and new class prototypes to avoid overfitting and forgetting, and batch-renormalization to cope with non-i.i.d.few-shot data. We create an extensive benchmark for iFSS showing that PIFS outperforms several few-shot and incremental learning methods in all scenarios.","url_abs":"https://arxiv.org/abs/2012.01415v2","url_pdf":"https://arxiv.org/pdf/2012.01415v2.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":"a-few-guidelines-for-incremental-few-shot","repo_url":"https://github.com/fcdl94/fss","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-image-segmentation","task_name":"Few-Shot Semantic Segmentation"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2012.01415","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}