{"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/incremental-few-shot-instance-segmentation","title":"Incremental Few-Shot Instance Segmentation","arxiv_id":"2105.05312","date":"2021-05-11","proceeding":"CVPR 2021 1","authors":["Dan Andrei Ganea","Bas Boom","Ronald Poppe"],"abstract":"Few-shot instance segmentation methods are promising when labeled training data for novel classes is scarce. However, current approaches do not facilitate flexible addition of novel classes. They also require that examples of each class are provided at train and test time, which is memory intensive. In this paper, we address these limitations by presenting the first incremental approach to few-shot instance segmentation: iMTFA. We learn discriminative embeddings for object instances that are merged into class representatives. Storing embedding vectors rather than images effectively solves the memory overhead problem. We match these class embeddings at the RoI-level using cosine similarity. This allows us to add new classes without the need for further training or access to previous training data. In a series of experiments, we consistently outperform the current state-of-the-art. Moreover, the reduced memory requirements allow us to evaluate, for the first time, few-shot instance segmentation performance on all classes in COCO jointly.","url_abs":"https://arxiv.org/abs/2105.05312v1","url_pdf":"https://arxiv.org/pdf/2105.05312v1.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":"incremental-few-shot-instance-segmentation","repo_url":"https://github.com/danganea/iMTFA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"few-shot-instance-segmentation","task_name":"Few-shot Instance Segmentation"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"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=2105.05312","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.05312"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/danganea/iMTFA","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"unverified":6},"by_repo_kind":{"official":{"samples":8,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":8,"samples":[{"code_sha256_prefix":"e8526a516b4f9206","entry":"convert_basic_c2_names","repo":"danganea/iMTFA","repo_kind":"official","path":"detectron2/checkpoint/c2_model_loading.py","file_url":"https://github.com/danganea/iMTFA/blob/HEAD/detectron2/checkpoint/c2_model_loading.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e8526a516b4f9206"}},{"code_sha256_prefix":"52810b504f0d1066","entry":"convert_c2_detectron_names","repo":"danganea/iMTFA","repo_kind":"official","path":"detectron2/checkpoint/c2_model_loading.py","file_url":"https://github.com/danganea/iMTFA/blob/HEAD/detectron2/checkpoint/c2_model_loading.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"52810b504f0d1066"}},{"code_sha256_prefix":"a450cf1cf2c15688","entry":"build_metadata_from_subsplit_COCO","repo":"danganea/iMTFA","repo_kind":"official","path":"OurPaper/dataset.py","file_url":"https://github.com/danganea/iMTFA/blob/HEAD/OurPaper/dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"a450cf1cf2c15688"}},{"code_sha256_prefix":"78cc0e83f654df22","entry":"get_COCO_subsplit","repo":"danganea/iMTFA","repo_kind":"official","path":"OurPaper/dataset.py","file_url":"https://github.com/danganea/iMTFA/blob/HEAD/OurPaper/dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"78cc0e83f654df22"}},{"code_sha256_prefix":"40d68dcf4b8e2a66","entry":"get_lastlayer_cls_score_bias","repo":"danganea/iMTFA","repo_kind":"official","path":"OurPaper/training.py","file_url":"https://github.com/danganea/iMTFA/blob/HEAD/OurPaper/training.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"40d68dcf4b8e2a66"}},{"code_sha256_prefix":"2d3d6103cb285053","entry":"get_lastlayer_mask_weights","repo":"danganea/iMTFA","repo_kind":"official","path":"OurPaper/training.py","file_url":"https://github.com/danganea/iMTFA/blob/HEAD/OurPaper/training.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"2d3d6103cb285053"}},{"code_sha256_prefix":"3560dd177ffcaeea","entry":"get_lastlayers_model_weights","repo":"danganea/iMTFA","repo_kind":"official","path":"OurPaper/training.py","file_url":"https://github.com/danganea/iMTFA/blob/HEAD/OurPaper/training.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"3560dd177ffcaeea"}},{"code_sha256_prefix":"fb6b8ecbce0b82a0","entry":"get_save_path_seeds","repo":"danganea/iMTFA","repo_kind":"official","path":"datasets/prepare_coco_few_shot.py","file_url":"https://github.com/danganea/iMTFA/blob/HEAD/datasets/prepare_coco_few_shot.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"fb6b8ecbce0b82a0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}