Mobile U-ViT: Revisiting large kernel and U-shaped ViT for efficient medical image segmentation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908477629136896 |
|---|---|
| author | Tang, Fenghe Nian, Bingkun Ding, Jianrui Ma, Wenxin Quan, Quan Dong, Chengqi Yang, Jie Liu, Wei Zhou, S. Kevin |
| author_facet | Tang, Fenghe Nian, Bingkun Ding, Jianrui Ma, Wenxin Quan, Quan Dong, Chengqi Yang, Jie Liu, Wei Zhou, S. Kevin |
| contents | In clinical practice, medical image analysis often requires efficient execution on resource-constrained mobile devices. However, existing mobile models-primarily optimized for natural images-tend to perform poorly on medical tasks due to the significant information density gap between natural and medical domains. Combining computational efficiency with medical imaging-specific architectural advantages remains a challenge when developing lightweight, universal, and high-performing networks. To address this, we propose a mobile model called Mobile U-shaped Vision Transformer (Mobile U-ViT) tailored for medical image segmentation. Specifically, we employ the newly purposed ConvUtr as a hierarchical patch embedding, featuring a parameter-efficient large-kernel CNN with inverted bottleneck fusion. This design exhibits transformer-like representation learning capacity while being lighter and faster. To enable efficient local-global information exchange, we introduce a novel Large-kernel Local-Global-Local (LGL) block that effectively balances the low information density and high-level semantic discrepancy of medical images. Finally, we incorporate a shallow and lightweight transformer bottleneck for long-range modeling and employ a cascaded decoder with downsample skip connections for dense prediction. Despite its reduced computational demands, our medical-optimized architecture achieves state-of-the-art performance across eight public 2D and 3D datasets covering diverse imaging modalities, including zero-shot testing on four unseen datasets. These results establish it as an efficient yet powerful and generalization solution for mobile medical image analysis. Code is available at https://github.com/FengheTan9/Mobile-U-ViT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_01064 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Mobile U-ViT: Revisiting large kernel and U-shaped ViT for efficient medical image segmentation Tang, Fenghe Nian, Bingkun Ding, Jianrui Ma, Wenxin Quan, Quan Dong, Chengqi Yang, Jie Liu, Wei Zhou, S. Kevin Image and Video Processing Computer Vision and Pattern Recognition In clinical practice, medical image analysis often requires efficient execution on resource-constrained mobile devices. However, existing mobile models-primarily optimized for natural images-tend to perform poorly on medical tasks due to the significant information density gap between natural and medical domains. Combining computational efficiency with medical imaging-specific architectural advantages remains a challenge when developing lightweight, universal, and high-performing networks. To address this, we propose a mobile model called Mobile U-shaped Vision Transformer (Mobile U-ViT) tailored for medical image segmentation. Specifically, we employ the newly purposed ConvUtr as a hierarchical patch embedding, featuring a parameter-efficient large-kernel CNN with inverted bottleneck fusion. This design exhibits transformer-like representation learning capacity while being lighter and faster. To enable efficient local-global information exchange, we introduce a novel Large-kernel Local-Global-Local (LGL) block that effectively balances the low information density and high-level semantic discrepancy of medical images. Finally, we incorporate a shallow and lightweight transformer bottleneck for long-range modeling and employ a cascaded decoder with downsample skip connections for dense prediction. Despite its reduced computational demands, our medical-optimized architecture achieves state-of-the-art performance across eight public 2D and 3D datasets covering diverse imaging modalities, including zero-shot testing on four unseen datasets. These results establish it as an efficient yet powerful and generalization solution for mobile medical image analysis. Code is available at https://github.com/FengheTan9/Mobile-U-ViT. |
| title | Mobile U-ViT: Revisiting large kernel and U-shaped ViT for efficient medical image segmentation |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.01064 |