{"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/a-compact-neural-architecture-for-visual","title":"A Hybrid Compact Neural Architecture for Visual Place Recognition","arxiv_id":"1910.06840","date":"2019-10-15","proceeding":null,"authors":["Marvin Chancán","Luis Hernandez-Nunez","Ajay Narendra","Andrew B. Barron","Michael Milford"],"abstract":"State-of-the-art algorithms for visual place recognition, and related visual navigation systems, can be broadly split into two categories: computer-science-oriented models including deep learning or image retrieval-based techniques with minimal biological plausibility, and neuroscience-oriented dynamical networks that model temporal properties underlying spatial navigation in the brain. In this letter, we propose a new compact and high-performing place recognition model that bridges this divide for the first time. Our approach comprises two key neural models of these categories: (1) FlyNet, a compact, sparse two-layer neural network inspired by brain architectures of fruit flies, Drosophila melanogaster, and (2) a one-dimensional continuous attractor neural network (CANN). The resulting FlyNet+CANN network incorporates the compact pattern recognition capabilities of our FlyNet model with the powerful temporal filtering capabilities of an equally compact CANN, replicating entirely in a hybrid neural implementation the functionality that yields high performance in algorithmic localization approaches like SeqSLAM. We evaluate our model, and compare it to three state-of-the-art methods, on two benchmark real-world datasets with small viewpoint variations and extreme environmental changes - achieving 87% AUC results under day to night transitions compared to 60% for Multi-Process Fusion, 46% for LoST-X and 1% for SeqSLAM, while being 6.5, 310, and 1.5 times faster, respectively.","url_abs":"https://arxiv.org/abs/1910.06840v3","url_pdf":"https://arxiv.org/pdf/1910.06840v3.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":"a-compact-neural-architecture-for-visual","repo_url":"https://github.com/uditsharma29/flynet-cann","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"autonomous-navigation","task_name":"Autonomous Navigation"},{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"motion-estimation","task_name":"Motion Estimation"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"robot-navigation","task_name":"Robot Navigation"},{"task_slug":"self-driving-cars","task_name":"Self-Driving Cars"},{"task_slug":"sequential-place-learning","task_name":"Sequential Place Learning"},{"task_slug":"sequential-place-recognition","task_name":"Sequential Place Recognition"},{"task_slug":"visual-localization","task_name":"Visual Localization"},{"task_slug":"visual-navigation","task_name":"Visual Navigation"},{"task_slug":"visual-place-recognition","task_name":"Visual Place Recognition"}],"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}