{"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/fully-trainable-deep-matching","title":"Fully-Trainable Deep Matching","arxiv_id":"1609.03532","date":"2016-09-12","proceeding":null,"authors":["James Thewlis","Shuai Zheng","Philip H. S. Torr","Andrea Vedaldi"],"abstract":"Deep Matching (DM) is a popular high-quality method for quasi-dense image\nmatching. Despite its name, however, the original DM formulation does not yield\na deep neural network that can be trained end-to-end via backpropagation. In\nthis paper, we remove this limitation by rewriting the complete DM algorithm as\na convolutional neural network. This results in a novel deep architecture for\nimage matching that involves a number of new layer types and that, similar to\nrecent networks for image segmentation, has a U-topology. We demonstrate the\nutility of the approach by improving the performance of DM by learning it\nend-to-end on an image matching task.","url_abs":"http://arxiv.org/abs/1609.03532v1","url_pdf":"http://arxiv.org/pdf/1609.03532v1.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":"fully-trainable-deep-matching","repo_url":"https://github.com/vwegn/dm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}