{"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/repeatability-is-not-enough-learning-affine","title":"Repeatability Is Not Enough: Learning Affine Regions via Discriminability","arxiv_id":"1711.06704","date":"2017-11-17","proceeding":"ECCV 2018 9","authors":["Dmytro Mishkin","Filip Radenovic","Jiri Matas"],"abstract":"A method for learning local affine-covariant regions is presented. We show\nthat maximizing geometric repeatability does not lead to local regions, a.k.a\nfeatures,that are reliably matched and this necessitates descriptor-based\nlearning. We explore factors that influence such learning and registration: the\nloss function, descriptor type, geometric parametrization and the trade-off\nbetween matchability and geometric accuracy and propose a novel hard\nnegative-constant loss function for learning of affine regions. The affine\nshape estimator -- AffNet -- trained with the hard negative-constant loss\noutperforms the state-of-the-art in bag-of-words image retrieval and wide\nbaseline stereo. The proposed training process does not require precisely\ngeometrically aligned patches.The source codes and trained weights are\navailable at https://github.com/ducha-aiki/affnet","url_abs":"http://arxiv.org/abs/1711.06704v4","url_pdf":"http://arxiv.org/pdf/1711.06704v4.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":"repeatability-is-not-enough-learning-affine","repo_url":"https://github.com/ducha-aiki/affnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"repeatability-is-not-enough-learning-affine","repo_url":"https://github.com/ducha-aiki/imc2021-sample-kornia-submission","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"repeatability-is-not-enough-learning-affine","repo_url":"https://github.com/kornia/kornia/blob/master/kornia/feature/affine_shape.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-matching","task_name":"Image Matching"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-matching-on-imc-phototourism","task":"Image Matching","dataset":"IMC PhotoTourism","model":"DoG-AffNet-HardNet8","rank_in_archive_order":4,"of":8,"metrics":{"mean average accuracy @ 10":"0.64212"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.06704","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}