Demystify Mamba in Vision: A Linear Attention Perspective

• URL: http://arxiv.org/abs/2405.16605v1
• Date: Sun, 26 May 2024 15:31:09 GMT
• Title: Demystify Mamba in Vision: A Linear Attention Perspective
• Authors: Dongchen Han, Ziyi Wang, Zhuofan Xia, Yizeng Han, Yifan Pu, Chunjiang Ge, Jun Song, Shiji Song, Bo Zheng, Gao Huang,
• Abstract summary: Mamba is an effective state space model with linear computation complexity. We show that Mamba shares surprising similarities with linear attention Transformer. We propose a Mamba-Like Linear Attention (MLLA) model by incorporating the merits of these two key designs into linear attention.
• Score: 72.93213667713493
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Mamba is an effective state space model with linear computation complexity. It has recently shown impressive efficiency in dealing with high-resolution inputs across various vision tasks. In this paper, we reveal that the powerful Mamba model shares surprising similarities with linear attention Transformer, which typically underperform conventional Transformer in practice. By exploring the similarities and disparities between the effective Mamba and subpar linear attention Transformer, we provide comprehensive analyses to demystify the key factors behind Mamba's success. Specifically, we reformulate the selective state space model and linear attention within a unified formulation, rephrasing Mamba as a variant of linear attention Transformer with six major distinctions: input gate, forget gate, shortcut, no attention normalization, single-head, and modified block design. For each design, we meticulously analyze its pros and cons, and empirically evaluate its impact on model performance in vision tasks. Interestingly, the results highlight the forget gate and block design as the core contributors to Mamba's success, while the other four designs are less crucial. Based on these findings, we propose a Mamba-Like Linear Attention (MLLA) model by incorporating the merits of these two key designs into linear attention. The resulting model outperforms various vision Mamba models in both image classification and high-resolution dense prediction tasks, while enjoying parallelizable computation and fast inference speed. Code is available at https://github.com/LeapLabTHU/MLLA.

Related papers

• MobileMamba: Lightweight Multi-Receptive Visual Mamba Network [51.33486891724516]
  Previous research on lightweight models has primarily focused on CNNs and Transformer-based designs. We propose the MobileMamba framework, which balances efficiency and performance. MobileMamba achieves up to 83.6% on Top-1, surpassing existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-11-24T18:01:05Z)
• KMM: Key Frame Mask Mamba for Extended Motion Generation [21.144913854895243]
  Key frame Masking Modeling is a novel architecture featuring Key frame Masking Modeling to enhance Mamba's focus on key actions in motion segments. We conduct extensive experiments on the go-to dataset, BABEL, achieving state-of-the-art performance with a reduction of more than 57% in FID and 70% parameters compared to previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-11-10T14:41:38Z)
• MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining [23.37555991996508]
  We propose Masked Autoregressive Pretraining (MAP) to pretrain a hybrid Mamba-Transformer vision backbone network. We show that both the pure Mamba architecture and the hybrid Mamba-Transformer vision backbone network pretrained with MAP significantly outperform other pretraining strategies.
  arXiv  Detail & Related papers  (2024-10-01T17:05:08Z)
• The Mamba in the Llama: Distilling and Accelerating Hybrid Models [76.64055251296548]
  We show that it is feasible to distill large Transformers into linear RNNs by reusing the linear projection weights from attention layers with academic GPU resources. The resulting hybrid model, which incorporates a quarter of the attention layers, achieves performance comparable to the original Transformer in chat benchmarks.
  arXiv  Detail & Related papers  (2024-08-27T17:56:11Z)
• An Empirical Study of Mamba-based Pedestrian Attribute Recognition [15.752464463535178]
  This paper designs and adapts Mamba into two typical PAR frameworks, text-image fusion approach and pure vision Mamba multi-label recognition framework. It is found that interacting with attribute tags as additional input does not always lead to an improvement, specifically, Vim can be enhanced, but VMamba cannot. These experimental results indicate that simply enhancing Mamba with a Transformer does not always lead to performance improvements but yields better results under certain settings.
  arXiv  Detail & Related papers  (2024-07-15T00:48:06Z)
• MambaVision: A Hybrid Mamba-Transformer Vision Backbone [54.965143338206644]
  We propose a novel hybrid Mamba-Transformer backbone, denoted as MambaVision, which is specifically tailored for vision applications. Our core contribution includes redesigning the Mamba formulation to enhance its capability for efficient modeling of visual features. We conduct a comprehensive ablation study on the feasibility of integrating Vision Transformers (ViT) with Mamba.
  arXiv  Detail & Related papers  (2024-07-10T23:02:45Z)
• Snakes and Ladders: Two Steps Up for VideoMamba [10.954210339694841]
  In this paper, we theoretically analyze the differences between self-attention and Mamba. We propose VideoMambaPro models that surpass VideoMamba by 1.6-2.8% and 1.1-1.9% top-1. Our two solutions are to recent advances in Vision Mamba models, and are likely to provide further improvements in future models.
  arXiv  Detail & Related papers  (2024-06-27T08:45:31Z)
• The Hidden Attention of Mamba Models [54.50526986788175]
  The Mamba layer offers an efficient selective state space model (SSM) that is highly effective in modeling multiple domains. We show that such models can be viewed as attention-driven models. This new perspective enables us to empirically and theoretically compare the underlying mechanisms to that of the self-attention layers in transformers.
  arXiv  Detail & Related papers  (2024-03-03T18:58:21Z)
• Is Mamba Capable of In-Context Learning? [63.682741783013306]
  State of the art foundation models such as GPT-4 perform surprisingly well at in-context learning (ICL) This work provides empirical evidence that Mamba, a newly proposed state space model, has similar ICL capabilities.
  arXiv  Detail & Related papers  (2024-02-05T16:39:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.