{"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-covariant-feature-detectors","title":"Learning Covariant Feature Detectors","arxiv_id":"1605.01224","date":"2016-05-04","proceeding":null,"authors":["Karel Lenc","Andrea Vedaldi"],"abstract":"Local covariant feature detection, namely the problem of extracting viewpoint\ninvariant features from images, has so far largely resisted the application of\nmachine learning techniques. In this paper, we propose the first fully general\nformulation for learning local covariant feature detectors. We propose to cast\ndetection as a regression problem, enabling the use of powerful regressors such\nas deep neural networks. We then derive a covariance constraint that can be\nused to automatically learn which visual structures provide stable anchors for\nlocal feature detection. We support these ideas theoretically, proposing a\nnovel analysis of local features in term of geometric transformations, and we\nshow that all common and many uncommon detectors can be derived in this\nframework. Finally, we present empirical results on translation and rotation\ncovariant detectors on standard feature benchmarks, showing the power and\nflexibility of the framework.","url_abs":"http://arxiv.org/abs/1605.01224v2","url_pdf":"http://arxiv.org/pdf/1605.01224v2.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-covariant-feature-detectors","repo_url":"https://github.com/lenck/ddet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1605.01224","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}