{"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/inverseform-a-loss-function-for-structured","title":"InverseForm: A Loss Function for Structured Boundary-Aware Segmentation","arxiv_id":"2104.02745","date":"2021-04-06","proceeding":"CVPR 2021 1","authors":["Shubhankar Borse","Ying Wang","Yizhe Zhang","Fatih Porikli"],"abstract":"We present a novel boundary-aware loss term for semantic segmentation using an inverse-transformation network, which efficiently learns the degree of parametric transformations between estimated and target boundaries. This plug-in loss term complements the cross-entropy loss in capturing boundary transformations and allows consistent and significant performance improvement on segmentation backbone models without increasing their size and computational complexity. We analyze the quantitative and qualitative effects of our loss function on three indoor and outdoor segmentation benchmarks, including Cityscapes, NYU-Depth-v2, and PASCAL, integrating it into the training phase of several backbone networks in both single-task and multi-task settings. Our extensive experiments show that the proposed method consistently outperforms baselines, and even sets the new state-of-the-art on two datasets.","url_abs":"https://arxiv.org/abs/2104.02745v2","url_pdf":"https://arxiv.org/pdf/2104.02745v2.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":"inverseform-a-loss-function-for-structured","repo_url":"https://github.com/Qualcomm-AI-research/InverseForm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"InverseForm","rank_in_archive_order":5,"of":105,"metrics":{"Mean IoU (class)":"85.6%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-nyu-depth-v2","task":"Semantic Segmentation","dataset":"NYU Depth v2","model":"InverseForm (ResNet-101)","rank_in_archive_order":40,"of":121,"metrics":{"Mean IoU":"53.1%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.02745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.02745"}},"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/Qualcomm-AI-research/InverseForm","reach":null}],"summary":{"ran":1,"unverified":2},"by_repo_kind":{"listed":{"samples":3,"ran":1,"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":3,"samples":[{"code_sha256_prefix":"bd2408d490b846b1","entry":"InverseNet","repo":"Qualcomm-AI-research/InverseForm","repo_kind":"listed","path":"models/loss/utils.py","file_url":"https://github.com/Qualcomm-AI-research/InverseForm/blob/HEAD/models/loss/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause-Clear","inline_ok":false,"mcp_get_code":{"code_sha256":"bd2408d490b846b1"}},{"code_sha256_prefix":"7c41eb28c82f38b5","entry":"InverseTransform2D","repo":"Qualcomm-AI-research/InverseForm","repo_kind":"listed","path":"models/loss/utils.py","file_url":"https://github.com/Qualcomm-AI-research/InverseForm/blob/HEAD/models/loss/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause-Clear","inline_ok":false,"mcp_get_code":{"code_sha256":"7c41eb28c82f38b5"}},{"code_sha256_prefix":"134ca0fd228f0fad","entry":"load_model_from_dict","repo":"Qualcomm-AI-research/InverseForm","repo_kind":"listed","path":"models/loss/utils.py","file_url":"https://github.com/Qualcomm-AI-research/InverseForm/blob/HEAD/models/loss/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause-Clear","inline_ok":false,"mcp_get_code":{"code_sha256":"134ca0fd228f0fad"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}