{"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/learning-robust-deep-face-representation","title":"Learning Robust Deep Face Representation","arxiv_id":"1507.04844","date":"2015-07-17","proceeding":null,"authors":["Xiang Wu"],"abstract":"With the development of convolution neural network, more and more researchers\nfocus their attention on the advantage of CNN for face recognition task. In\nthis paper, we propose a deep convolution network for learning a robust face\nrepresentation. The deep convolution net is constructed by 4 convolution\nlayers, 4 max pooling layers and 2 fully connected layers, which totally\ncontains about 4M parameters. The Max-Feature-Map activation function is used\ninstead of ReLU because the ReLU might lead to the loss of information due to\nthe sparsity while the Max-Feature-Map can get the compact and discriminative\nfeature vectors. The model is trained on CASIA-WebFace dataset and evaluated on\nLFW dataset. The result on LFW achieves 97.77% on unsupervised setting for\nsingle net.","url_abs":"http://arxiv.org/abs/1507.04844v1","url_pdf":"http://arxiv.org/pdf/1507.04844v1.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":"learning-robust-deep-face-representation","repo_url":"https://github.com/AlfredXiangWu/face_verification_experiment","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"face-recognition","task_name":"Face Recognition"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}