Bibliographic Details
| Title: |
MobileMamba: Lightweight Multi-Receptive Visual Mamba Network |
| Authors: |
He, Haoyang, Zhang, Jiangning, Cai, Yuxuan, Chen, Hongxu, Hu, Xiaobin, Gan, Zhenye, Wang, Yabiao, Wang, Chengjie, Wu, Yunsheng, Xie, Lei |
| Publication Year: |
2024 |
| Collection: |
Computer Science |
| Subject Terms: |
Computer Science - Computer Vision and Pattern Recognition |
| More Details: |
Previous research on lightweight models has primarily focused on CNNs and Transformer-based designs. CNNs, with their local receptive fields, struggle to capture long-range dependencies, while Transformers, despite their global modeling capabilities, are limited by quadratic computational complexity in high-resolution scenarios. Recently, state-space models have gained popularity in the visual domain due to their linear computational complexity. Despite their low FLOPs, current lightweight Mamba-based models exhibit suboptimal throughput. In this work, we propose the MobileMamba framework, which balances efficiency and performance. We design a three-stage network to enhance inference speed significantly. At a fine-grained level, we introduce the Multi-Receptive Field Feature Interaction(MRFFI) module, comprising the Long-Range Wavelet Transform-Enhanced Mamba(WTE-Mamba), Efficient Multi-Kernel Depthwise Convolution(MK-DeConv), and Eliminate Redundant Identity components. This module integrates multi-receptive field information and enhances high-frequency detail extraction. Additionally, we employ training and testing strategies to further improve performance and efficiency. MobileMamba achieves up to 83.6% on Top-1, surpassing existing state-of-the-art methods which is maximum x21 faster than LocalVim on GPU. Extensive experiments on high-resolution downstream tasks demonstrate that MobileMamba surpasses current efficient models, achieving an optimal balance between speed and accuracy.
Comment: 14 pages |
| Document Type: |
Working Paper |
| Access URL: |
http://arxiv.org/abs/2411.15941 |
| Accession Number: |
edsarx.2411.15941 |
| Database: |
arXiv |
