{"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/moon-a-mixed-objective-optimization-network","title":"MOON: A Mixed Objective Optimization Network for the Recognition of Facial Attributes","arxiv_id":"1603.07027","date":"2016-03-22","proceeding":null,"authors":["Ethan Rudd","Manuel Günther","Terrance Boult"],"abstract":"Attribute recognition, particularly facial, extracts many labels for each\nimage. While some multi-task vision problems can be decomposed into separate\ntasks and stages, e.g., training independent models for each task, for a\ngrowing set of problems joint optimization across all tasks has been shown to\nimprove performance. We show that for deep convolutional neural network (DCNN)\nfacial attribute extraction, multi-task optimization is better. Unfortunately,\nit can be difficult to apply joint optimization to DCNNs when training data is\nimbalanced, and re-balancing multi-label data directly is structurally\ninfeasible, since adding/removing data to balance one label will change the\nsampling of the other labels. This paper addresses the multi-label imbalance\nproblem by introducing a novel mixed objective optimization network (MOON) with\na loss function that mixes multiple task objectives with domain adaptive\nre-weighting of propagated loss. Experiments demonstrate that not only does\nMOON advance the state of the art in facial attribute recognition, but it also\noutperforms independently trained DCNNs using the same data. When using facial\nattributes for the LFW face recognition task, we show that our balanced (domain\nadapted) network outperforms the unbalanced trained network.","url_abs":"http://arxiv.org/abs/1603.07027v2","url_pdf":"http://arxiv.org/pdf/1603.07027v2.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":"moon-a-mixed-objective-optimization-network","repo_url":"https://github.com/camel007/caffe-moon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"moon-a-mixed-objective-optimization-network","repo_url":"https://github.com/feiyunzhang/person_attribute_mxnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"moon-a-mixed-objective-optimization-network","repo_url":"https://github.com/likelyzhao/peron_attribute","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"attribute-extraction","task_name":"Attribute Extraction"},{"task_slug":"face-recognition","task_name":"Face Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1603.07027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.07027"}},"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/likelyzhao/peron_attribute","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/feiyunzhang/person_attribute_mxnet","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/camel007/caffe-moon","reach":{"status":"ok"}}],"summary":{"unverified":4},"by_repo_kind":{"listed":{"samples":4,"ran":0,"repositories":2}},"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":"c93eb04d4abde37b","entry":"add_fit_args","repo":"likelyzhao/peron_attribute","repo_kind":"listed","path":"training/common/fit.py","file_url":"https://github.com/likelyzhao/peron_attribute/blob/HEAD/training/common/fit.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":"c93eb04d4abde37b"}},{"code_sha256_prefix":"3ef479bb5a86e5cc","entry":"download_file","repo":"likelyzhao/peron_attribute","repo_kind":"listed","path":"training/common/util.py","file_url":"https://github.com/likelyzhao/peron_attribute/blob/HEAD/training/common/util.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":"3ef479bb5a86e5cc"}},{"code_sha256_prefix":"94cd388ab0075451","entry":"get_epoch_size","repo":"likelyzhao/peron_attribute","repo_kind":"listed","path":"training/common/fit.py","file_url":"https://github.com/likelyzhao/peron_attribute/blob/HEAD/training/common/fit.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":"94cd388ab0075451"}},{"code_sha256_prefix":"471635a52c74215c","entry":"get_rec_lines","repo":"feiyunzhang/person_attribute_mxnet","repo_kind":"listed","path":"prepare_data/creat_pk_and_dk.py","file_url":"https://github.com/feiyunzhang/person_attribute_mxnet/blob/HEAD/prepare_data/creat_pk_and_dk.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":"471635a52c74215c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}