{"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/few-shot-segmentation-propagation-with-guided","title":"Few-Shot Segmentation Propagation with Guided Networks","arxiv_id":"1806.07373","date":"2018-05-25","proceeding":null,"authors":["Kate Rakelly","Evan Shelhamer","Trevor Darrell","Alexei A. Efros","Sergey Levine"],"abstract":"Learning-based methods for visual segmentation have made progress on\nparticular types of segmentation tasks, but are limited by the necessary\nsupervision, the narrow definitions of fixed tasks, and the lack of control\nduring inference for correcting errors. To remedy the rigidity and annotation\nburden of standard approaches, we address the problem of few-shot segmentation:\ngiven few image and few pixel supervision, segment any images accordingly. We\npropose guided networks, which extract a latent task representation from any\namount of supervision, and optimize our architecture end-to-end for fast,\naccurate few-shot segmentation. Our method can switch tasks without further\noptimization and quickly update when given more guidance. We report the first\nresults for segmentation from one pixel per concept and show real-time\ninteractive video segmentation. Our unified approach propagates pixel\nannotations across space for interactive segmentation, across time for video\nsegmentation, and across scenes for semantic segmentation. Our guided segmentor\nis state-of-the-art in accuracy for the amount of annotation and time. See\nhttp://github.com/shelhamer/revolver for code, models, and more details.","url_abs":"http://arxiv.org/abs/1806.07373v1","url_pdf":"http://arxiv.org/pdf/1806.07373v1.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":"few-shot-segmentation-propagation-with-guided","repo_url":"https://github.com/shelhamer/revolver","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[{"task_slug":"interactive-segmentation","task_name":"Interactive Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"video-segmentation","task_name":"Video Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1806.07373","atlas_url":"https://app.syntology.ai/?focus=1806.07373","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.07373"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/shelhamer/revolver","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":"580611037f2100b7","entry":"bilinear_kernel","repo":"shelhamer/revolver","repo_kind":"official","path":"revolver/model/fcn.py","file_url":"https://github.com/shelhamer/revolver/blob/HEAD/revolver/model/fcn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"580611037f2100b7"}},{"code_sha256_prefix":"8a8d094aaa42f654","entry":"convolutionalize","repo":"shelhamer/revolver","repo_kind":"official","path":"revolver/model/fcn.py","file_url":"https://github.com/shelhamer/revolver/blob/HEAD/revolver/model/fcn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"8a8d094aaa42f654"}},{"code_sha256_prefix":"71db8dcc6236c526","entry":"fast_hist","repo":"shelhamer/revolver","repo_kind":"official","path":"revolver/metrics.py","file_url":"https://github.com/shelhamer/revolver/blob/HEAD/revolver/metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"71db8dcc6236c526"}},{"code_sha256_prefix":"b1ed98232e8d10fa","entry":"vgg16","repo":"shelhamer/revolver","repo_kind":"official","path":"revolver/model/backbone.py","file_url":"https://github.com/shelhamer/revolver/blob/HEAD/revolver/model/backbone.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b1ed98232e8d10fa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}