{"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/discriminative-unsupervised-feature-learning","title":"Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks","arxiv_id":"1406.6909","date":"2014-06-26","proceeding":null,"authors":["Alexey Dosovitskiy","Philipp Fischer","Jost Tobias Springenberg","Martin Riedmiller","Thomas Brox"],"abstract":"Deep convolutional networks have proven to be very successful in learning\ntask specific features that allow for unprecedented performance on various\ncomputer vision tasks. Training of such networks follows mostly the supervised\nlearning paradigm, where sufficiently many input-output pairs are required for\ntraining. Acquisition of large training sets is one of the key challenges, when\napproaching a new task. In this paper, we aim for generic feature learning and\npresent an approach for training a convolutional network using only unlabeled\ndata. To this end, we train the network to discriminate between a set of\nsurrogate classes. Each surrogate class is formed by applying a variety of\ntransformations to a randomly sampled 'seed' image patch. In contrast to\nsupervised network training, the resulting feature representation is not class\nspecific. It rather provides robustness to the transformations that have been\napplied during training. This generic feature representation allows for\nclassification results that outperform the state of the art for unsupervised\nlearning on several popular datasets (STL-10, CIFAR-10, Caltech-101,\nCaltech-256). While such generic features cannot compete with class specific\nfeatures from supervised training on a classification task, we show that they\nare advantageous on geometric matching problems, where they also outperform the\nSIFT descriptor.","url_abs":"http://arxiv.org/abs/1406.6909v2","url_pdf":"http://arxiv.org/pdf/1406.6909v2.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":"discriminative-unsupervised-feature-learning","repo_url":"https://github.com/Octavio-Pappalardo/unsupervised-pretraining-via-self-classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"discriminative-unsupervised-feature-learning","repo_url":"https://github.com/Wuschelbueb/AML19-SelfSupervised","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"geometric-matching","task_name":"Geometric Matching"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1406.6909","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}