{"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/cu-net-coupled-u-nets","title":"CU-Net: Coupled U-Nets","arxiv_id":"1808.06521","date":"2018-08-20","proceeding":null,"authors":["Zhiqiang Tang","Xi Peng","Shijie Geng","Yizhe Zhu","Dimitris N. Metaxas"],"abstract":"We design a new connectivity pattern for the U-Net architecture. Given\nseveral stacked U-Nets, we couple each U-Net pair through the connections of\ntheir semantic blocks, resulting in the coupled U-Nets (CU-Net). The coupling\nconnections could make the information flow more efficiently across U-Nets. The\nfeature reuse across U-Nets makes each U-Net very parameter efficient. We\nevaluate the coupled U-Nets on two benchmark datasets of human pose estimation.\nBoth the accuracy and model parameter number are compared. The CU-Net obtains\ncomparable accuracy as state-of-the-art methods. However, it only has at least\n60% fewer parameters than other approaches.","url_abs":"http://arxiv.org/abs/1808.06521v1","url_pdf":"http://arxiv.org/pdf/1808.06521v1.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":"cu-net-coupled-u-nets","repo_url":"https://github.com/zhiqiangdon/CU-Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/pose-estimation-on-mpii-human-pose","task":"Pose Estimation","dataset":"MPII Human Pose","model":"CU-Net","rank_in_archive_order":30,"of":46,"metrics":{"PCKh-0.5":"89.4"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}