{"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/efficient-decentralized-visual-place","title":"Efficient Decentralized Visual Place Recognition From Full-Image Descriptors","arxiv_id":"1705.10739","date":"2017-05-30","proceeding":null,"authors":["Titus Cieslewski","Davide Scaramuzza"],"abstract":"In this paper, we discuss the adaptation of our decentralized place\nrecognition method described in [1] to full image descriptors. As we had shown,\nthe key to making a scalable decentralized visual place recognition lies in\nexploting deterministic key assignment in a distributed key-value map. Through\nthis, it is possible to reduce bandwidth by up to a factor of n, the robot\ncount, by casting visual place recognition to a key-value lookup problem. In\n[1], we exploited this for the bag-of-words method [3], [4]. Our method of\ncasting bag-of-words, however, results in a complex decentralized system, which\nhas inherently worse recall than its centralized counterpart. In this paper, we\ninstead start from the recent full-image description method NetVLAD [5]. As we\nshow, casting this to a key-value lookup problem can be achieved with k-means\nclustering, and results in a much simpler system than [1]. The resulting system\nstill has some flaws, albeit of a completely different nature: it suffers when\nthe environment seen during deployment lies in a different distribution in\nfeature space than the environment seen during training.","url_abs":"http://arxiv.org/abs/1705.10739v1","url_pdf":"http://arxiv.org/pdf/1705.10739v1.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":"efficient-decentralized-visual-place","repo_url":"https://github.com/uzh-rpg/dslam_open","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":null,"task_name":"Image Description"},{"task_slug":"visual-place-recognition","task_name":"Visual Place Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}