{"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/deepid3-face-recognition-with-very-deep","title":"DeepID3: Face Recognition with Very Deep Neural Networks","arxiv_id":"1502.00873","date":"2015-02-03","proceeding":null,"authors":["Yi Sun","Ding Liang","Xiaogang Wang","Xiaoou Tang"],"abstract":"The state-of-the-art of face recognition has been significantly advanced by\nthe emergence of deep learning. Very deep neural networks recently achieved\ngreat success on general object recognition because of their superb learning\ncapacity. This motivates us to investigate their effectiveness on face\nrecognition. This paper proposes two very deep neural network architectures,\nreferred to as DeepID3, for face recognition. These two architectures are\nrebuilt from stacked convolution and inception layers proposed in VGG net and\nGoogLeNet to make them suitable to face recognition. Joint face\nidentification-verification supervisory signals are added to both intermediate\nand final feature extraction layers during training. An ensemble of the\nproposed two architectures achieves 99.53% LFW face verification accuracy and\n96.0% LFW rank-1 face identification accuracy, respectively. A further\ndiscussion of LFW face verification result is given in the end.","url_abs":"http://arxiv.org/abs/1502.00873v1","url_pdf":"http://arxiv.org/pdf/1502.00873v1.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":"deepid3-face-recognition-with-very-deep","repo_url":"https://github.com/hqli/face_recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":{"status":"ok"}},{"paper_slug":"deepid3-face-recognition-with-very-deep","repo_url":"https://github.com/2023-MindSpore-1/ms-code-211/tree/main/DeepID","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"deepid3-face-recognition-with-very-deep","repo_url":"https://github.com/2023-MindSpore-4/Code2/tree/main/DeepID","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"deepid3-face-recognition-with-very-deep","repo_url":"https://github.com/MindSpore-paper-code-3/code2/tree/main/DeepID","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"deepid3-face-recognition-with-very-deep","repo_url":"https://github.com/MindSpore-paper-code-3/code8/tree/main/DeepID","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"deepid3-face-recognition-with-very-deep","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":"deepid3-face-recognition-with-very-deep","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":"deepid3-face-recognition-with-very-deep","repo_url":"https://github.com/code-implementation1/Code1/tree/main/DeepID","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"deepid3-face-recognition-with-very-deep","repo_url":"https://github.com/serengil/deepface","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"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":"object-recognition","task_name":"Object Recognition"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1502.00873","atlas_url":"https://app.syntology.ai/?focus=1502.00873","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}