{"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-classification-approach-towards","title":"A Classification approach towards Unsupervised Learning of Visual Representations","arxiv_id":"1806.00428","date":"2018-06-01","proceeding":null,"authors":["Aditya Vora"],"abstract":"In this paper, we present a technique for unsupervised learning of visual\nrepresentations. Specifically, we train a model for foreground and background\nclassification task, in the process of which it learns visual representations.\nForeground and background patches for training come af- ter mining for such\npatches from hundreds and thousands of unlabelled videos available on the web\nwhich we ex- tract using a proposed patch extraction algorithm. With- out using\nany supervision, with just using 150, 000 unla- belled videos and the PASCAL\nVOC 2007 dataset, we train a object recognition model that achieves 45.3 mAP\nwhich is close to the best performing unsupervised feature learn- ing technique\nwhereas better than many other proposed al- gorithms. The code for patch\nextraction is implemented in Matlab and available open source at the following\nlink .","url_abs":"http://arxiv.org/abs/1806.00428v1","url_pdf":"http://arxiv.org/pdf/1806.00428v1.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-classification-approach-towards","repo_url":"https://github.com/aditya-vora/unsupervised_patch_extraction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}