{"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/one-shot-instance-segmentation","title":"One-Shot Instance Segmentation","arxiv_id":"1811.11507","date":"2018-11-28","proceeding":null,"authors":["Claudio Michaelis","Ivan Ustyuzhaninov","Matthias Bethge","Alexander S. Ecker"],"abstract":"We tackle the problem of one-shot instance segmentation: Given an example image of a novel, previously unknown object category, find and segment all objects of this category within a complex scene. To address this challenging new task, we propose Siamese Mask R-CNN. It extends Mask R-CNN by a Siamese backbone encoding both reference image and scene, allowing it to target detection and segmentation towards the reference category. We demonstrate empirical results on MS Coco highlighting challenges of the one-shot setting: while transferring knowledge about instance segmentation to novel object categories works very well, targeting the detection network towards the reference category appears to be more difficult. Our work provides a first strong baseline for one-shot instance segmentation and will hopefully inspire further research into more powerful and flexible scene analysis algorithms. Code is available at: https://github.com/bethgelab/siamese-mask-rcnn","url_abs":"https://arxiv.org/abs/1811.11507v2","url_pdf":"https://arxiv.org/pdf/1811.11507v2.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":"one-shot-instance-segmentation","repo_url":"https://github.com/bethgelab/siamese-mask-rcnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"one-shot-instance-segmentation","repo_url":"https://github.com/ducminhkhoi/FAPIS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"one-shot-instance-segmentation","repo_url":"https://github.com/michaelisc/cluttered-omniglot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"few-shot-object-detection","task_name":"Few-Shot Object Detection"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"one-shot-instance-segmentation","task_name":"One-Shot Instance Segmentation"},{"task_slug":"one-shot-learning","task_name":"One-Shot Learning"},{"task_slug":"one-shot-object-detection","task_name":"One-Shot Object Detection"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"mask-r-cnn","method_name":"Mask R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/one-shot-instance-segmentation-on-coco","task":"One-Shot Instance Segmentation","dataset":"COCO (Common Objects in Context)","model":"Siamese Mask R-CNN","rank_in_archive_order":1,"of":1,"metrics":{"AP 0.5":"14.5"},"uses_additional_data":false},{"leaderboard":"/sota/one-shot-object-detection-on-coco","task":"One-Shot Object Detection","dataset":"COCO (Common Objects in Context)","model":"Siamese Mask R-CNN","rank_in_archive_order":4,"of":4,"metrics":{"AP 0.5":"16.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.11507","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.11507"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bethgelab/siamese-mask-rcnn","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/michaelisc/cluttered-omniglot","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ducminhkhoi/FAPIS","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":6},"by_repo_kind":{"listed":{"samples":6,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"b43f9531c8913da6","entry":"batch_transformer","repo":"michaelisc/cluttered-omniglot","repo_kind":"listed","path":"spatial_transformer.py","file_url":"https://github.com/michaelisc/cluttered-omniglot/blob/HEAD/spatial_transformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b43f9531c8913da6"}},{"code_sha256_prefix":"94ba0b96fdbf5b4f","entry":"center_of_mass","repo":"michaelisc/cluttered-omniglot","repo_kind":"listed","path":"model.py","file_url":"https://github.com/michaelisc/cluttered-omniglot/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"94ba0b96fdbf5b4f"}},{"code_sha256_prefix":"3dd4093b9ce74332","entry":"prepare_char","repo":"michaelisc/cluttered-omniglot","repo_kind":"listed","path":"dataset_utils.py","file_url":"https://github.com/michaelisc/cluttered-omniglot/blob/HEAD/dataset_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3dd4093b9ce74332"}},{"code_sha256_prefix":"85a56f46fc1baef1","entry":"rot_x","repo":"michaelisc/cluttered-omniglot","repo_kind":"listed","path":"dataset_utils.py","file_url":"https://github.com/michaelisc/cluttered-omniglot/blob/HEAD/dataset_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"85a56f46fc1baef1"}},{"code_sha256_prefix":"3ca30e21ff4521c6","entry":"rot_y","repo":"michaelisc/cluttered-omniglot","repo_kind":"listed","path":"dataset_utils.py","file_url":"https://github.com/michaelisc/cluttered-omniglot/blob/HEAD/dataset_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ca30e21ff4521c6"}},{"code_sha256_prefix":"6f411210f7e3c47c","entry":"transformer","repo":"michaelisc/cluttered-omniglot","repo_kind":"listed","path":"spatial_transformer.py","file_url":"https://github.com/michaelisc/cluttered-omniglot/blob/HEAD/spatial_transformer.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6f411210f7e3c47c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}