{"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/star-loss-reducing-semantic-ambiguity-in-1","title":"STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection","arxiv_id":"2306.02763","date":"2023-06-05","proceeding":"CVPR 2023 1","authors":["Zhenglin Zhou","Huaxia Li","Hong Liu","Nanyang Wang","Gang Yu","Rongrong Ji"],"abstract":"Recently, deep learning-based facial landmark detection has achieved significant improvement. However, the semantic ambiguity problem degrades detection performance. Specifically, the semantic ambiguity causes inconsistent annotation and negatively affects the model's convergence, leading to worse accuracy and instability prediction. To solve this problem, we propose a Self-adapTive Ambiguity Reduction (STAR) loss by exploiting the properties of semantic ambiguity. We find that semantic ambiguity results in the anisotropic predicted distribution, which inspires us to use predicted distribution to represent semantic ambiguity. Based on this, we design the STAR loss that measures the anisotropism of the predicted distribution. Compared with the standard regression loss, STAR loss is encouraged to be small when the predicted distribution is anisotropic and thus adaptively mitigates the impact of semantic ambiguity. Moreover, we propose two kinds of eigenvalue restriction methods that could avoid both distribution's abnormal change and the model's premature convergence. Finally, the comprehensive experiments demonstrate that STAR loss outperforms the state-of-the-art methods on three benchmarks, i.e., COFW, 300W, and WFLW, with negligible computation overhead. Code is at https://github.com/ZhenglinZhou/STAR.","url_abs":"https://arxiv.org/abs/2306.02763v1","url_pdf":"https://arxiv.org/pdf/2306.02763v1.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":"star-loss-reducing-semantic-ambiguity-in-1","repo_url":"https://github.com/zhenglinzhou/star","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"face-alignment","task_name":"Face Alignment"},{"task_slug":"facial-landmark-detection","task_name":"Facial Landmark Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/face-alignment-on-300w","task":"Face Alignment","dataset":"300W","model":"STAR","rank_in_archive_order":1,"of":48,"metrics":{"NME_inter-ocular (%, Challenge)":"4.32","NME_inter-ocular (%, Common)":"2.52","NME_inter-ocular (%, Full)":"2.87","NME_inter-pupil (%, Challenge)":"6.22","NME_inter-pupil (%, Common)":"3.5","NME_inter-pupil (%, Full)":"4.03"},"uses_additional_data":false},{"leaderboard":"/sota/face-alignment-on-cofw","task":"Face Alignment","dataset":"COFW","model":"STAR","rank_in_archive_order":6,"of":28,"metrics":{"NME (inter-ocular)":"3.21%","NME (inter-pupil)":"4.62"},"uses_additional_data":false},{"leaderboard":"/sota/face-alignment-on-wflw","task":"Face Alignment","dataset":"WFLW","model":"STAR","rank_in_archive_order":3,"of":36,"metrics":{"AUC@10 (inter-ocular)":"60.5","FR@10 (inter-ocular)":"2.32","NME (inter-ocular)":"4.02"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.02763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02763"}},"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/zhenglinzhou/star","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/ZhenglinZhou/STAR","reach":{"status":"ok"}}],"summary":{"ran":3,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":4,"samples":[{"code_sha256_prefix":"3d5cd766c436c11e","entry":"STARLoss","repo":"ZhenglinZhou/STAR","repo_kind":"official","path":"lib/loss/starLoss.py","file_url":"https://github.com/ZhenglinZhou/STAR/blob/HEAD/lib/loss/starLoss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3d5cd766c436c11e"}},{"code_sha256_prefix":"18f933cd26f8dc6f","entry":"SmoothL1Loss","repo":"ZhenglinZhou/STAR","repo_kind":"official","path":"lib/loss/starLoss.py","file_url":"https://github.com/ZhenglinZhou/STAR/blob/HEAD/lib/loss/starLoss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"18f933cd26f8dc6f"}},{"code_sha256_prefix":"25539617aa20a2b6","entry":"WingLoss","repo":"ZhenglinZhou/STAR","repo_kind":"official","path":"lib/loss/starLoss.py","file_url":"https://github.com/ZhenglinZhou/STAR/blob/HEAD/lib/loss/starLoss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"25539617aa20a2b6"}},{"code_sha256_prefix":"044141f88224c379","entry":"expand_two_dimensions_at_end","repo":"ZhenglinZhou/STAR","repo_kind":"official","path":"lib/loss/starLoss.py","file_url":"https://github.com/ZhenglinZhou/STAR/blob/HEAD/lib/loss/starLoss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"044141f88224c379"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}