{"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/a-light-cnn-for-deep-face-representation-with","title":"A Light CNN for Deep Face Representation with Noisy Labels","arxiv_id":"1511.02683","date":"2015-11-09","proceeding":null,"authors":["Xiang Wu","Ran He","Zhenan Sun","Tieniu Tan"],"abstract":"The volume of convolutional neural network (CNN) models proposed for face\nrecognition has been continuously growing larger to better fit large amount of\ntraining data. When training data are obtained from internet, the labels are\nlikely to be ambiguous and inaccurate. This paper presents a Light CNN\nframework to learn a compact embedding on the large-scale face data with\nmassive noisy labels. First, we introduce a variation of maxout activation,\ncalled Max-Feature-Map (MFM), into each convolutional layer of CNN. Different\nfrom maxout activation that uses many feature maps to linearly approximate an\narbitrary convex activation function, MFM does so via a competitive\nrelationship. MFM can not only separate noisy and informative signals but also\nplay the role of feature selection between two feature maps. Second, three\nnetworks are carefully designed to obtain better performance meanwhile reducing\nthe number of parameters and computational costs. Lastly, a semantic\nbootstrapping method is proposed to make the prediction of the networks more\nconsistent with noisy labels. Experimental results show that the proposed\nframework can utilize large-scale noisy data to learn a Light model that is\nefficient in computational costs and storage spaces. The learned single network\nwith a 256-D representation achieves state-of-the-art results on various face\nbenchmarks without fine-tuning. The code is released on\nhttps://github.com/AlfredXiangWu/LightCNN.","url_abs":"http://arxiv.org/abs/1511.02683v4","url_pdf":"http://arxiv.org/pdf/1511.02683v4.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":"a-light-cnn-for-deep-face-representation-with","repo_url":"https://github.com/AlfredXiangWu/LightCNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-light-cnn-for-deep-face-representation-with","repo_url":"https://github.com/AlfredXiangWu/face_verification_experiment","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-light-cnn-for-deep-face-representation-with","repo_url":"https://github.com/Mind23-2/MindCode-56","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":null},{"paper_slug":"a-light-cnn-for-deep-face-representation-with","repo_url":"https://github.com/gcastex/PruNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-light-cnn-for-deep-face-representation-with","repo_url":"https://github.com/lyatdawn/lightcnn-mxnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok"}},{"paper_slug":"a-light-cnn-for-deep-face-representation-with","repo_url":"https://github.com/ozora-ogino/LCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-light-cnn-for-deep-face-representation-with","repo_url":"https://github.com/yxu0611/tensorflow-implementation-of-lcnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"a-light-cnn-for-deep-face-representation-with","repo_url":"https://dagshub.com/Bharat-mtr/LightCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"a-light-cnn-for-deep-face-representation-with","repo_url":"https://github.com/2023-MindSpore-1/ms-code-18/tree/main/LightCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"a-light-cnn-for-deep-face-representation-with","repo_url":"https://github.com/2023-MindSpore-4/Code-5/tree/main/LightCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"a-light-cnn-for-deep-face-representation-with","repo_url":"https://github.com/Asthestarsfalll/LightCNN-MegEngine","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-light-cnn-for-deep-face-representation-with","repo_url":"https://github.com/FaceOnLive/Face-Recognition-SDK-Android","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"a-light-cnn-for-deep-face-representation-with","repo_url":"https://github.com/Faceplugin-ltd/FaceRecognition-Android","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"a-light-cnn-for-deep-face-representation-with","repo_url":"https://github.com/Mind23-2/MindCode-101/tree/main/LightCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"a-light-cnn-for-deep-face-representation-with","repo_url":"https://github.com/Mind23-2/MindCode-3/tree/main/LightCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"a-light-cnn-for-deep-face-representation-with","repo_url":"https://github.com/Recognito-Vision/Android-FaceRecognition-FaceLivenessDetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"a-light-cnn-for-deep-face-representation-with","repo_url":"https://github.com/Recognito-Vision/Linux-FaceRecognition-FaceLivenessDetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"a-light-cnn-for-deep-face-representation-with","repo_url":"https://github.com/code-implementation1/Code4/tree/main/LightCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"a-light-cnn-for-deep-face-representation-with","repo_url":"https://github.com/mindspore-ai/models/blob/master/research/cv/LightCNN/","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"face-identification","task_name":"Face Identification"},{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"face-verification","task_name":"Face Verification"},{"task_slug":"image-editing-dection","task_name":"Image Editing Dection"},{"task_slug":"feature-selection","task_name":"feature selection"}],"methods":[{"method_slug":"maxout","method_name":"Maxout"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/age-invariant-face-recognition-on-cacdvs","task":"Age-Invariant Face Recognition","dataset":"CACDVS","model":"MFM-CNN","rank_in_archive_order":8,"of":9,"metrics":{"Accuracy":"97.95%"},"uses_additional_data":false},{"leaderboard":"/sota/age-invariant-face-recognition-on-cafr","task":"Age-Invariant Face Recognition","dataset":"CAFR","model":"Light CNN","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"73.56%"},"uses_additional_data":false},{"leaderboard":"/sota/face-identification-on-megaface","task":"Face Identification","dataset":"MegaFace","model":"Light CNN-29","rank_in_archive_order":11,"of":13,"metrics":{"Accuracy":"73.749%"},"uses_additional_data":false},{"leaderboard":"/sota/face-verification-on-megaface","task":"Face Verification","dataset":"MegaFace","model":"Light CNN-29","rank_in_archive_order":12,"of":12,"metrics":{"Accuracy":"85.133%"},"uses_additional_data":false},{"leaderboard":"/sota/face-verification-on-youtube-faces-db","task":"Face Verification","dataset":"YouTube Faces DB","model":"Light CNN-29","rank_in_archive_order":7,"of":12,"metrics":{"Accuracy":"95.54%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.02683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.02683"}},"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/Recognito-Vision/Linux-FaceRecognition-FaceLivenessDetection","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-ai/models/blob/master/research/cv/LightCNN/","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lyatdawn/lightcnn-mxnet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AlfredXiangWu/face_verification_experiment","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mind23-2/MindCode-3/tree/main/LightCNN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/FaceOnLive/Face-Recognition-SDK-Android","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yxu0611/tensorflow-implementation-of-lcnn","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Asthestarsfalll/LightCNN-MegEngine","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/code-implementation1/Code4/tree/main/LightCNN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-1/ms-code-18/tree/main/LightCNN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AlfredXiangWu/LightCNN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Recognito-Vision/Android-FaceRecognition-FaceLivenessDetection","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gcastex/PruNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Faceplugin-ltd/FaceRecognition-Android","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mind23-2/MindCode-101/tree/main/LightCNN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mind23-2/MindCode-56","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-4/Code-5/tree/main/LightCNN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://dagshub.com/Bharat-mtr/LightCNN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ozora-ogino/LCNN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"7b0d61a663a3d558","entry":"clip_gradient","repo":"Mind23-2/MindCode-56","repo_kind":"listed","path":"src/lightcnn.py","file_url":"https://github.com/Mind23-2/MindCode-56/blob/HEAD/src/lightcnn.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7b0d61a663a3d558"}},{"code_sha256_prefix":"4a6362e1eee5a452","entry":"read_list","repo":"AlfredXiangWu/LightCNN","repo_kind":"official","path":"extract_features.py","file_url":"https://github.com/AlfredXiangWu/LightCNN/blob/HEAD/extract_features.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4a6362e1eee5a452"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}