{"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/all-you-need-are-a-few-pixels-semantic","title":"All you need are a few pixels: semantic segmentation with PixelPick","arxiv_id":"2104.06394","date":"2021-04-13","proceeding":null,"authors":["Gyungin Shin","Weidi Xie","Samuel Albanie"],"abstract":"A central challenge for the task of semantic segmentation is the prohibitive cost of obtaining dense pixel-level annotations to supervise model training. In this work, we show that in order to achieve a good level of segmentation performance, all you need are a few well-chosen pixel labels. We make the following contributions: (i) We investigate the novel semantic segmentation setting in which labels are supplied only at sparse pixel locations, and show that deep neural networks can use a handful of such labels to good effect; (ii) We demonstrate how to exploit this phenomena within an active learning framework, termed PixelPick, to radically reduce labelling cost, and propose an efficient \"mouse-free\" annotation strategy to implement our approach; (iii) We conduct extensive experiments to study the influence of annotation diversity under a fixed budget, model pretraining, model capacity and the sampling mechanism for picking pixels in this low annotation regime; (iv) We provide comparisons to the existing state of the art in semantic segmentation with active learning, and demonstrate comparable performance with up to two orders of magnitude fewer pixel annotations on the CamVid, Cityscapes and PASCAL VOC 2012 benchmarks; (v) Finally, we evaluate the efficiency of our annotation pipeline and its sensitivity to annotator error to demonstrate its practicality.","url_abs":"https://arxiv.org/abs/2104.06394v2","url_pdf":"https://arxiv.org/pdf/2104.06394v2.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":"all-you-need-are-a-few-pixels-semantic","repo_url":"https://github.com/NoelShin/PixelPick","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"all-you-need-are-a-few-pixels-semantic","repo_url":"https://github.com/yazdaniamir38/madbal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"task_slug":"all","task_name":"All"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.06394","atlas_url":"https://app.syntology.ai/?focus=2104.06394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.06394"}},"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/NoelShin/PixelPick","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yazdaniamir38/madbal","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"unverified":6},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1},"listed":{"samples":6,"ran":5,"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":"c204954f25139fdd","entry":"get_weights","repo":"yazdaniamir38/madbal","repo_kind":"listed","path":"utils/losses.py","file_url":"https://github.com/yazdaniamir38/madbal/blob/HEAD/utils/losses.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c204954f25139fdd"}},{"code_sha256_prefix":"3d38fe989e7b40c1","entry":"make_one_hot","repo":"yazdaniamir38/madbal","repo_kind":"listed","path":"utils/losses.py","file_url":"https://github.com/yazdaniamir38/madbal/blob/HEAD/utils/losses.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3d38fe989e7b40c1"}},{"code_sha256_prefix":"b68a8578f8b27ceb","entry":"mse_loss","repo":"yazdaniamir38/madbal","repo_kind":"listed","path":"utils/losses.py","file_url":"https://github.com/yazdaniamir38/madbal/blob/HEAD/utils/losses.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b68a8578f8b27ceb"}},{"code_sha256_prefix":"d9286f5f6bd943b4","entry":"multi_scale_predict","repo":"yazdaniamir38/madbal","repo_kind":"listed","path":"inference_VOC.py","file_url":"https://github.com/yazdaniamir38/madbal/blob/HEAD/inference_VOC.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d9286f5f6bd943b4"}},{"code_sha256_prefix":"b62891686b976239","entry":"pad_image","repo":"yazdaniamir38/madbal","repo_kind":"listed","path":"inference_VOC.py","file_url":"https://github.com/yazdaniamir38/madbal/blob/HEAD/inference_VOC.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b62891686b976239"}},{"code_sha256_prefix":"c704648bd87c532f","entry":"build_aspp","repo":"NoelShin/PixelPick","repo_kind":"official","path":"networks/aspp.py","file_url":"https://github.com/NoelShin/PixelPick/blob/HEAD/networks/aspp.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":"c704648bd87c532f"}},{"code_sha256_prefix":"8cf426bba4e98da5","entry":"conv_bn","repo":"NoelShin/PixelPick","repo_kind":"official","path":"networks/mobilenet_v2.py","file_url":"https://github.com/NoelShin/PixelPick/blob/HEAD/networks/mobilenet_v2.py","link_basis":"harvester_set","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":"8cf426bba4e98da5"}},{"code_sha256_prefix":"b34c12741c44b60c","entry":"fixed_padding","repo":"NoelShin/PixelPick","repo_kind":"official","path":"networks/mobilenet_v2.py","file_url":"https://github.com/NoelShin/PixelPick/blob/HEAD/networks/mobilenet_v2.py","link_basis":"harvester_set","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":"b34c12741c44b60c"}},{"code_sha256_prefix":"693791a46cc3f42c","entry":"gather_previous_query_files","repo":"NoelShin/PixelPick","repo_kind":"official","path":"query.py","file_url":"https://github.com/NoelShin/PixelPick/blob/HEAD/query.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":"693791a46cc3f42c"}},{"code_sha256_prefix":"116373e2bac7614d","entry":"merge_previous_query_files","repo":"NoelShin/PixelPick","repo_kind":"official","path":"query.py","file_url":"https://github.com/NoelShin/PixelPick/blob/HEAD/query.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":"116373e2bac7614d"}},{"code_sha256_prefix":"ae60cffe1b0b7d5b","entry":"sliding_predict","repo":"yazdaniamir38/madbal","repo_kind":"listed","path":"inference_VOC.py","file_url":"https://github.com/yazdaniamir38/madbal/blob/HEAD/inference_VOC.py","link_basis":"harvester_set","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":"ae60cffe1b0b7d5b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}