{"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/auto-seg-loss-searching-metric-surrogates-for-1","title":"Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation","arxiv_id":"2010.07930","date":"2020-10-15","proceeding":"ICLR 2021 1","authors":["Hao Li","Chenxin Tao","Xizhou Zhu","Xiaogang Wang","Gao Huang","Jifeng Dai"],"abstract":"Designing proper loss functions is essential in training deep networks. Especially in the field of semantic segmentation, various evaluation metrics have been proposed for diverse scenarios. Despite the success of the widely adopted cross-entropy loss and its variants, the mis-alignment between the loss functions and evaluation metrics degrades the network performance. Meanwhile, manually designing loss functions for each specific metric requires expertise and significant manpower. In this paper, we propose to automate the design of metric-specific loss functions by searching differentiable surrogate losses for each metric. We substitute the non-differentiable operations in the metrics with parameterized functions, and conduct parameter search to optimize the shape of loss surfaces. Two constraints are introduced to regularize the search space and make the search efficient. Extensive experiments on PASCAL VOC and Cityscapes demonstrate that the searched surrogate losses outperform the manually designed loss functions consistently. The searched losses can generalize well to other datasets and networks. Code shall be released.","url_abs":"https://arxiv.org/abs/2010.07930v2","url_pdf":"https://arxiv.org/pdf/2010.07930v2.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":"auto-seg-loss-searching-metric-surrogates-for-1","repo_url":"https://github.com/fundamentalvision/Auto-Seg-Loss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2010.07930","atlas_url":"https://app.syntology.ai/?focus=2010.07930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.07930"}},"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/fundamentalvision/Auto-Seg-Loss","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":6,"unverified":3},"by_repo_kind":{"listed":{"samples":9,"ran":6,"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":"6467b6d3f3fca80f","entry":"flatten_binary_logits","repo":"fundamentalvision/Auto-Seg-Loss","repo_kind":"listed","path":"mmseg/models/losses/lovasz_loss.py","file_url":"https://github.com/fundamentalvision/Auto-Seg-Loss/blob/HEAD/mmseg/models/losses/lovasz_loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6467b6d3f3fca80f"}},{"code_sha256_prefix":"e028f43bbba9e8c0","entry":"flatten_probs","repo":"fundamentalvision/Auto-Seg-Loss","repo_kind":"listed","path":"mmseg/models/losses/lovasz_loss.py","file_url":"https://github.com/fundamentalvision/Auto-Seg-Loss/blob/HEAD/mmseg/models/losses/lovasz_loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e028f43bbba9e8c0"}},{"code_sha256_prefix":"cca418ad92c39b3c","entry":"forward_FWIoU","repo":"fundamentalvision/Auto-Seg-Loss","repo_kind":"listed","path":"mmseg/models/losses/auto_seg_loss.py","file_url":"https://github.com/fundamentalvision/Auto-Seg-Loss/blob/HEAD/mmseg/models/losses/auto_seg_loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cca418ad92c39b3c"}},{"code_sha256_prefix":"4c08ad2c74b46974","entry":"forward_mIoU","repo":"fundamentalvision/Auto-Seg-Loss","repo_kind":"listed","path":"mmseg/models/losses/auto_seg_loss.py","file_url":"https://github.com/fundamentalvision/Auto-Seg-Loss/blob/HEAD/mmseg/models/losses/auto_seg_loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4c08ad2c74b46974"}},{"code_sha256_prefix":"87e40f2872a4cfa5","entry":"lovasz_grad","repo":"fundamentalvision/Auto-Seg-Loss","repo_kind":"listed","path":"mmseg/models/losses/lovasz_loss.py","file_url":"https://github.com/fundamentalvision/Auto-Seg-Loss/blob/HEAD/mmseg/models/losses/lovasz_loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"87e40f2872a4cfa5"}},{"code_sha256_prefix":"098b6c18149bbccf","entry":"map_to_one_hot","repo":"fundamentalvision/Auto-Seg-Loss","repo_kind":"listed","path":"mmseg/models/losses/auto_seg_loss.py","file_url":"https://github.com/fundamentalvision/Auto-Seg-Loss/blob/HEAD/mmseg/models/losses/auto_seg_loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"098b6c18149bbccf"}},{"code_sha256_prefix":"c2c6075384f7da61","entry":"binary_cross_entropy","repo":"fundamentalvision/Auto-Seg-Loss","repo_kind":"listed","path":"mmseg/models/losses/cross_entropy_loss.py","file_url":"https://github.com/fundamentalvision/Auto-Seg-Loss/blob/HEAD/mmseg/models/losses/cross_entropy_loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c2c6075384f7da61"}},{"code_sha256_prefix":"505a1e5bfde0143b","entry":"cross_entropy","repo":"fundamentalvision/Auto-Seg-Loss","repo_kind":"listed","path":"mmseg/models/losses/cross_entropy_loss.py","file_url":"https://github.com/fundamentalvision/Auto-Seg-Loss/blob/HEAD/mmseg/models/losses/cross_entropy_loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"505a1e5bfde0143b"}},{"code_sha256_prefix":"9dd6cc0f7220b833","entry":"mask_cross_entropy","repo":"fundamentalvision/Auto-Seg-Loss","repo_kind":"listed","path":"mmseg/models/losses/cross_entropy_loss.py","file_url":"https://github.com/fundamentalvision/Auto-Seg-Loss/blob/HEAD/mmseg/models/losses/cross_entropy_loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9dd6cc0f7220b833"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}