{"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/unsupervised-feature-learning-for-dense","title":"Unsupervised Feature Learning for Dense Correspondences across Scenes","arxiv_id":"1501.00642","date":"2015-01-04","proceeding":null,"authors":["Chao Zhang","Chunhua Shen","Tingzhi Shen"],"abstract":"We propose a fast, accurate matching method for estimating dense pixel\ncorrespondences across scenes. It is a challenging problem to estimate dense\npixel correspondences between images depicting different scenes or instances of\nthe same object category. While most such matching methods rely on hand-crafted\nfeatures such as SIFT, we learn features from a large amount of unlabeled image\npatches using unsupervised learning. Pixel-layer features are obtained by\nencoding over the dictionary, followed by spatial pooling to obtain patch-layer\nfeatures. The learned features are then seamlessly embedded into a multi-layer\nmatch- ing framework. We experimentally demonstrate that the learned features,\ntogether with our matching model, outperforms state-of-the-art methods such as\nthe SIFT flow, coherency sensitive hashing and the recent deformable spatial\npyramid matching methods both in terms of accuracy and computation efficiency.\nFurthermore, we evaluate the performance of a few different dictionary learning\nand feature encoding methods in the proposed pixel correspondences estimation\nframework, and analyse the impact of dictionary learning and feature encoding\nwith respect to the final matching performance.","url_abs":"http://arxiv.org/abs/1501.00642v2","url_pdf":"http://arxiv.org/pdf/1501.00642v2.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":"unsupervised-feature-learning-for-dense","repo_url":"https://bitbucket.org/chhshen/ufl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"dictionary-learning","task_name":"Dictionary Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}