{"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/pn-net-conjoined-triple-deep-network-for","title":"PN-Net: Conjoined Triple Deep Network for Learning Local Image Descriptors","arxiv_id":"1601.05030","date":"2016-01-19","proceeding":null,"authors":["Vassileios Balntas","Edward Johns","Lilian Tang","Krystian Mikolajczyk"],"abstract":"In this paper we propose a new approach for learning local descriptors for\nmatching image patches. It has recently been demonstrated that descriptors\nbased on convolutional neural networks (CNN) can significantly improve the\nmatching performance. Unfortunately their computational complexity is\nprohibitive for any practical application. We address this problem and propose\na CNN based descriptor with improved matching performance, significantly\nreduced training and execution time, as well as low dimensionality.\n  We propose to train the network with triplets of patches that include a\npositive and negative pairs. To that end we introduce a new loss function that\nexploits the relations within the triplets. We compare our approach to recently\nintroduced MatchNet and DeepCompare and demonstrate the advantages of our\ndescriptor in terms of performance, memory footprint and speed i.e. when run in\nGPU, the extraction time of our 128 dimensional feature is comparable to the\nfastest available binary descriptors such as BRIEF and ORB.","url_abs":"http://arxiv.org/abs/1601.05030v1","url_pdf":"http://arxiv.org/pdf/1601.05030v1.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":"pn-net-conjoined-triple-deep-network-for","repo_url":"https://github.com/vbalnt/pnnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1601.05030","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}