MambaU-Lite: A Lightweight Model based on Mamba and Integrated Channel-Spatial Attention for Skin Lesion Segmentation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913594147340288 |
|---|---|
| author | Nguyen, Thi-Nhu-Quynh Ho, Quang-Huy Nguyen, Duy-Thai Le, Hoang-Minh-Quang Pham, Van-Truong Tran, Thi-Thao |
| author_facet | Nguyen, Thi-Nhu-Quynh Ho, Quang-Huy Nguyen, Duy-Thai Le, Hoang-Minh-Quang Pham, Van-Truong Tran, Thi-Thao |
| contents | Early detection of skin abnormalities plays a crucial role in diagnosing and treating skin cancer. Segmentation of affected skin regions using AI-powered devices is relatively common and supports the diagnostic process. However, achieving high performance remains a significant challenge due to the need for high-resolution images and the often unclear boundaries of individual lesions. At the same time, medical devices require segmentation models to have a small memory foot-print and low computational cost. Based on these requirements, we introduce a novel lightweight model called MambaU-Lite, which combines the strengths of Mamba and CNN architectures, featuring just over 400K parameters and a computational cost of more than 1G flops. To enhance both global context and local feature extraction, we propose the P-Mamba block, a novel component that incorporates VSS blocks along-side multiple pooling layers, enabling the model to effectively learn multiscale features and enhance segmentation performance. We evaluate the model's performance on two skin datasets, ISIC2018 and PH2, yielding promising results. Our source code will be made publicly available at: https://github.com/nqnguyen812/MambaU-Lite. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_01405 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MambaU-Lite: A Lightweight Model based on Mamba and Integrated Channel-Spatial Attention for Skin Lesion Segmentation Nguyen, Thi-Nhu-Quynh Ho, Quang-Huy Nguyen, Duy-Thai Le, Hoang-Minh-Quang Pham, Van-Truong Tran, Thi-Thao Computer Vision and Pattern Recognition Artificial Intelligence Early detection of skin abnormalities plays a crucial role in diagnosing and treating skin cancer. Segmentation of affected skin regions using AI-powered devices is relatively common and supports the diagnostic process. However, achieving high performance remains a significant challenge due to the need for high-resolution images and the often unclear boundaries of individual lesions. At the same time, medical devices require segmentation models to have a small memory foot-print and low computational cost. Based on these requirements, we introduce a novel lightweight model called MambaU-Lite, which combines the strengths of Mamba and CNN architectures, featuring just over 400K parameters and a computational cost of more than 1G flops. To enhance both global context and local feature extraction, we propose the P-Mamba block, a novel component that incorporates VSS blocks along-side multiple pooling layers, enabling the model to effectively learn multiscale features and enhance segmentation performance. We evaluate the model's performance on two skin datasets, ISIC2018 and PH2, yielding promising results. Our source code will be made publicly available at: https://github.com/nqnguyen812/MambaU-Lite. |
| title | MambaU-Lite: A Lightweight Model based on Mamba and Integrated Channel-Spatial Attention for Skin Lesion Segmentation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2412.01405 |