{"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material modified by Syntology; see the attribution page"},"url":"/paper/u-net-vs-transformer-is-u-net-outdated-in","title":"U-Net vs Transformer: Is U-Net Outdated in Medical Image Registration?","arxiv_id":"2208.04939","date":"2022-08-07","proceeding":null,"authors":["Xi Jia","Joseph Bartlett","Tianyang Zhang","Wenqi Lu","Zhaowen Qiu","Jinming Duan"],"abstract":"Due to their extreme long-range modeling capability, vision transformer-based networks have become increasingly popular in deformable image registration. We believe, however, that the receptive field of a 5-layer convolutional U-Net is sufficient to capture accurate deformations without needing long-range dependencies. The purpose of this study is therefore to investigate whether U-Net-based methods are outdated compared to modern transformer-based approaches when applied to medical image registration. For this, we propose a large kernel U-Net (LKU-Net) by embedding a parallel convolutional block to a vanilla U-Net in order to enhance the effective receptive field. On the public 3D IXI brain dataset for atlas-based registration, we show that the performance of the vanilla U-Net is already comparable with that of state-of-the-art transformer-based networks (such as TransMorph), and that the proposed LKU-Net outperforms TransMorph by using only 1.12% of its parameters and 10.8% of its mult-adds operations. We further evaluate LKU-Net on a MICCAI Learn2Reg 2021 challenge dataset for inter-subject registration, our LKU-Net also outperforms TransMorph on this dataset and ranks first on the public leaderboard as of the submission of this work. With only modest modifications to the vanilla U-Net, we show that U-Net can outperform transformer-based architectures on inter-subject and atlas-based 3D medical image registration. Code is available at https://github.com/xi-jia/LKU-Net.","url_abs":"https://arxiv.org/abs/2208.04939v2","url_pdf":"https://arxiv.org/pdf/2208.04939v2.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":"u-net-vs-transformer-is-u-net-outdated-in","repo_url":"https://github.com/xi-jia/lku-net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-registration","task_name":"Image Registration"},{"task_slug":"long-range-modeling","task_name":"Long-range modeling"},{"task_slug":"medical-image-registration","task_name":"Medical Image Registration"}],"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":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2208.04939","atlas_url":"https://app.syntology.ai/?focus=2208.04939","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}