{"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/semantic-instance-segmentation-with-a","title":"Semantic Instance Segmentation with a Discriminative Loss Function","arxiv_id":"1708.02551","date":"2017-08-08","proceeding":null,"authors":["Bert De Brabandere","Davy Neven","Luc van Gool"],"abstract":"Semantic instance segmentation remains a challenging task. In this work we\npropose to tackle the problem with a discriminative loss function, operating at\nthe pixel level, that encourages a convolutional network to produce a\nrepresentation of the image that can easily be clustered into instances with a\nsimple post-processing step. The loss function encourages the network to map\neach pixel to a point in feature space so that pixels belonging to the same\ninstance lie close together while different instances are separated by a wide\nmargin. Our approach of combining an off-the-shelf network with a principled\nloss function inspired by a metric learning objective is conceptually simple\nand distinct from recent efforts in instance segmentation. In contrast to\nprevious works, our method does not rely on object proposals or recurrent\nmechanisms. A key contribution of our work is to demonstrate that such a simple\nsetup without bells and whistles is effective and can perform on par with more\ncomplex methods. Moreover, we show that it does not suffer from some of the\nlimitations of the popular detect-and-segment approaches. We achieve\ncompetitive performance on the Cityscapes and CVPPP leaf segmentation\nbenchmarks.","url_abs":"http://arxiv.org/abs/1708.02551v1","url_pdf":"http://arxiv.org/pdf/1708.02551v1.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":"semantic-instance-segmentation-with-a","repo_url":"https://github.com/NaturalHistoryMuseum/semantic-segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"semantic-instance-segmentation-with-a","repo_url":"https://github.com/Wizaron/instance-segmentation-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"semantic-instance-segmentation-with-a","repo_url":"https://github.com/alicranck/instance-seg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"semantic-instance-segmentation-with-a","repo_url":"https://github.com/davyneven/fastSceneUnderstanding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"semantic-instance-segmentation-with-a","repo_url":"https://github.com/gymoon10/Instance-Segmentation-with-Discriminative-Loss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"semantic-instance-segmentation-with-a","repo_url":"https://github.com/harryhan618/LaneNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"semantic-instance-segmentation-with-a","repo_url":"https://github.com/hq-jiang/instance-segmentation-with-discriminative-loss-tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"semantic-instance-segmentation-with-a","repo_url":"https://github.com/nyoki-mtl/pytorch-discriminative-loss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"lane-detection","task_name":"Lane Detection"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"multi-human-parsing","task_name":"Multi-Human Parsing"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/instance-segmentation-on-cityscapes","task":"Instance Segmentation","dataset":"Cityscapes test","model":"Semantic Instance Segmentation with a Discriminative Loss Function","rank_in_archive_order":8,"of":11,"metrics":{},"uses_additional_data":false},{"leaderboard":"/sota/lane-detection-on-tusimple","task":"Lane Detection","dataset":"TuSimple","model":"Discriminative loss function","rank_in_archive_order":20,"of":43,"metrics":{"Accuracy":"96.40%"},"uses_additional_data":false},{"leaderboard":"/sota/multi-human-parsing-on-mhp-v10","task":"Multi-Human Parsing","dataset":"MHP v1.0","model":"DL","rank_in_archive_order":4,"of":4,"metrics":{"AP 0.5":"47.76%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.02551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.02551"}},"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/nyoki-mtl/pytorch-discriminative-loss","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/davyneven/fastSceneUnderstanding","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gymoon10/Instance-Segmentation-with-Discriminative-Loss","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/harryhan618/LaneNet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hq-jiang/instance-segmentation-with-discriminative-loss-tensorflow","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NaturalHistoryMuseum/semantic-segmentation","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Wizaron/instance-segmentation-pytorch","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alicranck/instance-seg","reach":null}],"summary":{"unverified":2},"by_repo_kind":{"listed":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"477ccc1239988b3e","entry":"config_experiment","repo":"alicranck/instance-seg","repo_kind":"listed","path":"config.py","file_url":"https://github.com/alicranck/instance-seg/blob/HEAD/config.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"477ccc1239988b3e"}},{"code_sha256_prefix":"7f13f9caa2722e71","entry":"config_logger","repo":"alicranck/instance-seg","repo_kind":"listed","path":"config.py","file_url":"https://github.com/alicranck/instance-seg/blob/HEAD/config.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7f13f9caa2722e71"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}