{"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/an-accurate-retrieval-through-r-mac","title":"An accurate retrieval through R-MAC+ descriptors for landmark recognition","arxiv_id":"1806.08565","date":"2018-06-22","proceeding":null,"authors":["Federico Magliani","Andrea Prati"],"abstract":"The landmark recognition problem is far from being solved, but with the use\nof features extracted from intermediate layers of Convolutional Neural Networks\n(CNNs), excellent results have been obtained. In this work, we propose some\nimprovements on the creation of R-MAC descriptors in order to make the\nnewly-proposed R-MAC+ descriptors more representative than the previous ones.\nHowever, the main contribution of this paper is a novel retrieval technique,\nthat exploits the fine representativeness of the MAC descriptors of the\ndatabase images. Using this descriptors called \"db regions\" during the\nretrieval stage, the performance is greatly improved. The proposed method is\ntested on different public datasets: Oxford5k, Paris6k and Holidays. It\noutperforms the state-of-the- art results on Holidays and reached excellent\nresults on Oxford5k and Paris6k, overcame only by approaches based on\nfine-tuning strategies.","url_abs":"http://arxiv.org/abs/1806.08565v1","url_pdf":"http://arxiv.org/pdf/1806.08565v1.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":"an-accurate-retrieval-through-r-mac","repo_url":"https://github.com/fmaglia/keras_rmac_plus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"landmark-recognition","task_name":"Landmark Recognition"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}