{"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/unsupervised-learning-of-face-representations","title":"Unsupervised Learning of Face Representations","arxiv_id":"1803.01260","date":"2018-03-03","proceeding":null,"authors":["Samyak Datta","Gaurav Sharma","C. V. Jawahar"],"abstract":"We present an approach for unsupervised training of CNNs in order to learn\ndiscriminative face representations. We mine supervised training data by noting\nthat multiple faces in the same video frame must belong to different persons\nand the same face tracked across multiple frames must belong to the same\nperson. We obtain millions of face pairs from hundreds of videos without using\nany manual supervision. Although faces extracted from videos have a lower\nspatial resolution than those which are available as part of standard\nsupervised face datasets such as LFW and CASIA-WebFace, the former represent a\nmuch more realistic setting, e.g. in surveillance scenarios where most of the\nfaces detected are very small. We train our CNNs with the relatively low\nresolution faces extracted from video frames collected, and achieve a higher\nverification accuracy on the benchmark LFW dataset cf. hand-crafted features\nsuch as LBPs, and even surpasses the performance of state-of-the-art deep\nnetworks such as VGG-Face, when they are made to work with low resolution input\nimages.","url_abs":"http://arxiv.org/abs/1803.01260v1","url_pdf":"http://arxiv.org/pdf/1803.01260v1.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":"unsupervised-learning-of-face-representations","repo_url":"https://github.com/jiarenchang/facecycle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.01260","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}