{"ID":2865324,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.22307","arxiv_id":"2509.22307","title":"Johnson-Lindenstrauss Lemma Guided Network for Efficient 3D Medical Segmentation","abstract":"Lightweight 3D medical image segmentation remains constrained by a fundamental \"efficiency / robustness conflict\", particularly when processing complex anatomical structures and heterogeneous modalities. In this paper, we study how to redesign the framework based on the characteristics of high-dimensional 3D images, and explore data synergy to overcome the fragile representation of lightweight methods. Our approach, VeloxSeg, begins with a deployable and extensible dual-stream CNN-Transformer architecture composed of Paired Window Attention (PWA) and Johnson-Lindenstrauss lemma-guided convolution (JLC). For each 3D image, we invoke a \"glance-and-focus\" principle, where PWA rapidly retrieves multi-scale information, and JLC ensures robust local feature extraction with minimal parameters, significantly enhancing the model's ability to operate with low computational budget. Followed by an extension of the dual-stream architecture that incorporates modal interaction into the multi-scale image-retrieval process, VeloxSeg efficiently models heterogeneous modalities. Finally, Spatially Decoupled Knowledge Transfer (SDKT) via Gram matrices injects the texture prior extracted by a self-supervised network into the segmentation network, yielding stronger representations than baselines at no extra inference cost. Experimental results on multimodal benchmarks show that VeloxSeg achieves a 26% Dice improvement, alongside increasing GPU throughput by 11x and CPU by 48x. Codes are available at https://github.com/JinPLu/VeloxSeg.","short_abstract":"Lightweight 3D medical image segmentation remains constrained by a fundamental \"efficiency / robustness conflict\", particularly when processing complex anatomical structures and heterogeneous modalities. In this paper, we study how to redesign the framework based on the characteristics of high-dimensional 3D images, an...","url_abs":"https://arxiv.org/abs/2509.22307","url_pdf":"https://arxiv.org/pdf/2509.22307v1","authors":"[\"Jinpeng Lu\",\"Linghan Cai\",\"Yinda Chen\",\"Guo Tang\",\"Songhan Jiang\",\"Haoyuan Shi\",\"Zhiwei Xiong\"]","published":"2025-09-26T13:12:43Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\",\"Convolutional Neural Network\"]","has_code":false,"code_links":[{"ID":609260,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2865324,"paper_url":"https://arxiv.org/abs/2509.22307","paper_title":"Johnson-Lindenstrauss Lemma Guided Network for Efficient 3D Medical Segmentation","repo_url":"https://github.com/JinPLu/VeloxSeg","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}