{"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/understanding-and-improving-kernel-local","title":"Understanding and Improving Kernel Local Descriptors","arxiv_id":"1811.11147","date":"2018-11-27","proceeding":null,"authors":["Arun Mukundan","Giorgos Tolias","Andrei Bursuc","Hervé Jégou","Ondřej Chum"],"abstract":"We propose a multiple-kernel local-patch descriptor based on efficient match\nkernels from pixel gradients. It combines two parametrizations of gradient\nposition and direction, each parametrization provides robustness to a different\ntype of patch mis-registration: polar parametrization for noise in the patch\ndominant orientation detection, Cartesian for imprecise location of the feature\npoint. Combined with whitening of the descriptor space, that is learned with or\nwithout supervision, the performance is significantly improved. We analyze the\neffect of the whitening on patch similarity and demonstrate its semantic\nmeaning. Our unsupervised variant is the best performing descriptor constructed\nwithout the need of labeled data. Despite the simplicity of the proposed\ndescriptor, it competes well with deep learning approaches on a number of\ndifferent tasks.","url_abs":"http://arxiv.org/abs/1811.11147v1","url_pdf":"http://arxiv.org/pdf/1811.11147v1.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":"understanding-and-improving-kernel-local","repo_url":"https://github.com/manyids2/mkd_local_descriptor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"understanding-and-improving-kernel-local","repo_url":"https://github.com/manyids2/mkd_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"understanding-and-improving-kernel-local","repo_url":"https://github.com/kornia/kornia/blob/master/kornia/feature/mkd.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"Position"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}