{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mobilemamba-lightweight-multi-receptive","title":"MobileMamba: Lightweight Multi-Receptive Visual Mamba Network","arxiv_id":"2411.15941","date":"2024-11-24","proceeding":"CVPR 2025 1","authors":["Haoyang He","Jiangning Zhang","Yuxuan Cai","Hongxu Chen","Xiaobin Hu","Zhenye Gan","Yabiao Wang","Chengjie Wang","Yunsheng Wu","Lei Xie"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2411.15941v1","url_pdf":"https://arxiv.org/pdf/2411.15941v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mobilemamba-lightweight-multi-receptive","repo_url":"https://github.com/lewandofskee/MobileMamba","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"mamba","task_name":"Mamba"},{"task_slug":"state-space-models","task_name":"State Space Models"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}