{"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/nu-litenet-mobile-landmark-recognition-using","title":"NU-LiteNet: Mobile Landmark Recognition using Convolutional Neural Networks","arxiv_id":"1810.01074","date":"2018-10-02","proceeding":null,"authors":["Chakkrit Termritthikun","Surachet Kanprachar","Paisarn Muneesawang"],"abstract":"The growth of high-performance mobile devices has resulted in more research\ninto on-device image recognition. The research problems are the latency and\naccuracy of automatic recognition, which remains obstacles to its real-world\nusage. Although the recently developed deep neural networks can achieve\naccuracy comparable to that of a human user, some of them still lack the\nnecessary latency. This paper describes the development of the architecture of\na new convolutional neural network model, NU-LiteNet. For this, SqueezeNet was\ndeveloped to reduce the model size to a degree suitable for smartphones. The\nmodel size of NU-LiteNet is therefore 2.6 times smaller than that of\nSqueezeNet. The recognition accuracy of NU-LiteNet also compared favorably with\nother recently developed deep neural networks, when experiments were conducted\non two standard landmark databases.","url_abs":"http://arxiv.org/abs/1810.01074v1","url_pdf":"http://arxiv.org/pdf/1810.01074v1.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":"nu-litenet-mobile-landmark-recognition-using","repo_url":"https://github.com/chakkritte/NU-LiteNet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"landmark-recognition","task_name":"Landmark Recognition"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"fire-module","method_name":"Fire Module"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"squeezenet","method_name":"SqueezeNet"},{"method_slug":"xavier-initialization","method_name":"Xavier Initialization"}],"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}