Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2509.22307 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911178407542784 |
|---|---|
| author | Lu, Jinpeng Cai, Linghan Chen, Yinda Tang, Guo Jiang, Songhan Shi, Haoyuan Xiong, Zhiwei |
| author_facet | Lu, Jinpeng Cai, Linghan Chen, Yinda Tang, Guo Jiang, Songhan Shi, Haoyuan Xiong, Zhiwei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_22307 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Johnson-Lindenstrauss Lemma Guided Network for Efficient 3D Medical Segmentation Lu, Jinpeng Cai, Linghan Chen, Yinda Tang, Guo Jiang, Songhan Shi, Haoyuan Xiong, Zhiwei Computer Vision and Pattern Recognition 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. |
| title | Johnson-Lindenstrauss Lemma Guided Network for Efficient 3D Medical Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.22307 |