MicroViT: A Vision Transformer with Low Complexity Self Attention for Edge Device
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909671079542784 |
|---|---|
| author | Setyawan, Novendra Sun, Chi-Chia Hsu, Mao-Hsiu Kuo, Wen-Kai Hsieh, Jun-Wei |
| author_facet | Setyawan, Novendra Sun, Chi-Chia Hsu, Mao-Hsiu Kuo, Wen-Kai Hsieh, Jun-Wei |
| contents | The Vision Transformer (ViT) has demonstrated state-of-the-art performance in various computer vision tasks, but its high computational demands make it impractical for edge devices with limited resources. This paper presents MicroViT, a lightweight Vision Transformer architecture optimized for edge devices by significantly reducing computational complexity while maintaining high accuracy. The core of MicroViT is the Efficient Single Head Attention (ESHA) mechanism, which utilizes group convolution to reduce feature redundancy and processes only a fraction of the channels, thus lowering the burden of the self-attention mechanism. MicroViT is designed using a multi-stage MetaFormer architecture, stacking multiple MicroViT encoders to enhance efficiency and performance. Comprehensive experiments on the ImageNet-1K and COCO datasets demonstrate that MicroViT achieves competitive accuracy while significantly improving 3.6 faster inference speed and reducing energy consumption with 40% higher efficiency than the MobileViT series, making it suitable for deployment in resource-constrained environments such as mobile and edge devices. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_05800 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MicroViT: A Vision Transformer with Low Complexity Self Attention for Edge Device Setyawan, Novendra Sun, Chi-Chia Hsu, Mao-Hsiu Kuo, Wen-Kai Hsieh, Jun-Wei Computer Vision and Pattern Recognition The Vision Transformer (ViT) has demonstrated state-of-the-art performance in various computer vision tasks, but its high computational demands make it impractical for edge devices with limited resources. This paper presents MicroViT, a lightweight Vision Transformer architecture optimized for edge devices by significantly reducing computational complexity while maintaining high accuracy. The core of MicroViT is the Efficient Single Head Attention (ESHA) mechanism, which utilizes group convolution to reduce feature redundancy and processes only a fraction of the channels, thus lowering the burden of the self-attention mechanism. MicroViT is designed using a multi-stage MetaFormer architecture, stacking multiple MicroViT encoders to enhance efficiency and performance. Comprehensive experiments on the ImageNet-1K and COCO datasets demonstrate that MicroViT achieves competitive accuracy while significantly improving 3.6 faster inference speed and reducing energy consumption with 40% higher efficiency than the MobileViT series, making it suitable for deployment in resource-constrained environments such as mobile and edge devices. |
| title | MicroViT: A Vision Transformer with Low Complexity Self Attention for Edge Device |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.05800 |