SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks

• URL: http://arxiv.org/abs/2409.09649v1
• Date: Sun, 15 Sep 2024 07:46:18 GMT
• Title: SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks
• Authors: Meng Lou, Yunxiang Fu, Yizhou Yu,
• Abstract summary: This paper introduces an efficient cross-layer feature aggregation mechanism for Mamba-based vision backbone networks. Inspired by the Retinal Ganglion Cells (RGCs) in the human visual system, we propose a new sparse cross-layer connection mechanism termed SparX. Our new connection mechanism possesses both superior performance and generalization capabilities on various vision tasks.
• Score: 45.68176825375723
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Due to the capability of dynamic state space models (SSMs) in capturing long-range dependencies with near-linear computational complexity, Mamba has shown notable performance in NLP tasks. This has inspired the rapid development of Mamba-based vision models, resulting in promising results in visual recognition tasks. However, such models are not capable of distilling features across layers through feature aggregation, interaction, and selection. Moreover, existing cross-layer feature aggregation methods designed for CNNs or ViTs are not practical in Mamba-based models due to high computational costs. Therefore, this paper aims to introduce an efficient cross-layer feature aggregation mechanism for Mamba-based vision backbone networks. Inspired by the Retinal Ganglion Cells (RGCs) in the human visual system, we propose a new sparse cross-layer connection mechanism termed SparX to effectively improve cross-layer feature interaction and reuse. Specifically, we build two different types of network layers: ganglion layers and normal layers. The former has higher connectivity and complexity, enabling multi-layer feature aggregation and interaction in an input-dependent manner. In contrast, the latter has lower connectivity and complexity. By interleaving these two types of layers, we design a new vision backbone network with sparsely cross-connected layers, achieving an excellent trade-off among model size, computational cost, memory cost, and accuracy in comparison to its counterparts. For instance, with fewer parameters, SparX-Mamba-T improves the top-1 accuracy of VMamba-T from 82.5% to 83.5%, while SparX-Swin-T achieves a 1.3% increase in top-1 accuracy compared to Swin-T. Extensive experimental results demonstrate that our new connection mechanism possesses both superior performance and generalization capabilities on various vision tasks.

Related papers

• Multiscale Tensor Summation Factorization as a New Neural Network Layer (MTS Layer) for Multidimensional Data Processing [18.557169937152967]
  Multiscale Summation (MTS) Factorization is a novel neural network operator that implements tensor summation at multiple scales. MTS not only reduces the number of parameters required while enhancing the efficiency of weight optimization, but it also demonstrates clear advantages over convolutional layers. The corresponding neural network, MTSNet, demonstrates a more favorable complexity-performance tradeoff compared to state-of-the-art transformers in various computer vision applications.
  arXiv  Detail & Related papers  (2025-04-17T22:19:59Z)
• vGamba: Attentive State Space Bottleneck for efficient Long-range Dependencies in Visual Recognition [0.0]
  State-space models (SSMs) offer an alternative, but their application in vision remains underexplored. This work introduces vGamba, a hybrid vision backbone that integrates SSMs with attention mechanisms to enhance efficiency and expressiveness. Tests on classification, detection, and segmentation tasks demonstrate that vGamba achieves a superior trade-off between accuracy and computational efficiency, outperforming several existing models.
  arXiv  Detail & Related papers  (2025-03-27T08:39:58Z)
• A Comparative Study on Dynamic Graph Embedding based on Mamba and Transformers [0.29687381456164]
  This study presents a comparative analysis of dynamic graph embedding approaches using transformers and the recently proposed Mamba architecture. We introduce three novel models: TransformerG2G augment with graph convolutional networks, DG-Mamba, and GDG-Mamba with graph isomorphism network edge convolutions. Our experiments on multiple benchmark datasets demonstrate that Mamba-based models achieve comparable or superior performance to transformer-based approaches in link prediction tasks.
  arXiv  Detail & Related papers  (2024-12-15T19:56:56Z)
• 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)
• Bidirectional Gated Mamba for Sequential Recommendation [56.85338055215429]
  Mamba, a recent advancement, has exhibited exceptional performance in time series prediction. We introduce a new framework named Selective Gated Mamba ( SIGMA) for Sequential Recommendation. Our results indicate that SIGMA outperforms current models on five real-world datasets.
  arXiv  Detail & Related papers  (2024-08-21T09:12:59Z)
• Mamba-Spike: Enhancing the Mamba Architecture with a Spiking Front-End for Efficient Temporal Data Processing [4.673285689826945]
  Mamba-Spike is a novel neuromorphic architecture that integrates a spiking front-end with the Mamba backbone to achieve efficient temporal data processing. The architecture consistently outperforms state-of-the-art baselines, achieving higher accuracy, lower latency, and improved energy efficiency.
  arXiv  Detail & Related papers  (2024-08-04T14:10:33Z)
• Mamba-in-Mamba: Centralized Mamba-Cross-Scan in Tokenized Mamba Model for Hyperspectral Image Classification [4.389334324926174]
  This study introduces the innovative Mamba-in-Mamba (MiM) architecture for HSI classification, the first attempt of deploying State Space Model (SSM) in this task. MiM model includes 1) A novel centralized Mamba-Cross-Scan (MCS) mechanism for transforming images into sequence-data, 2) A Tokenized Mamba (T-Mamba) encoder, and 3) A Weighted MCS Fusion (WMF) module. Experimental results from three public HSI datasets demonstrate that our method outperforms existing baselines and state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-05-20T13:19:02Z)
• Integrating Mamba Sequence Model and Hierarchical Upsampling Network for Accurate Semantic Segmentation of Multiple Sclerosis Legion [0.0]
  We introduce Mamba HUNet, a novel architecture tailored for robust and efficient segmentation tasks. We first converted HUNet into a lighter version, maintaining performance parity and then integrated this lighter HUNet into Mamba HUNet, further enhancing its efficiency. Experimental results on publicly available Magnetic Resonance Imaging scans, notably in Multiple Sclerosis lesion segmentation, demonstrate Mamba HUNet's effectiveness across diverse segmentation tasks.
  arXiv  Detail & Related papers  (2024-03-26T06:57:50Z)
• EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba [19.062950348441426]
  This work proposes to explore the potential of visual state space models in light-weight model design and introduce a novel efficient model variant dubbed EfficientVMamba. Our EfficientVMamba integrates a atrous-based selective scan approach by efficient skip sampling, constituting building blocks designed to harness both global and local representational features. Experimental results show that, EfficientVMamba scales down the computational complexity while yields competitive results across a variety of vision tasks.
  arXiv  Detail & Related papers  (2024-03-15T02:48:47Z)
• Heterogenous Memory Augmented Neural Networks [84.29338268789684]
  We introduce a novel heterogeneous memory augmentation approach for neural networks. By introducing learnable memory tokens with attention mechanism, we can effectively boost performance without huge computational overhead. We show our approach on various image and graph-based tasks under both in-distribution (ID) and out-of-distribution (OOD) conditions.
  arXiv  Detail & Related papers  (2023-10-17T01:05:28Z)
• A Generic Shared Attention Mechanism for Various Backbone Neural Networks [53.36677373145012]
  Self-attention modules (SAMs) produce strongly correlated attention maps across different layers. Dense-and-Implicit Attention (DIA) shares SAMs across layers and employs a long short-term memory module. Our simple yet effective DIA can consistently enhance various network backbones.
  arXiv  Detail & Related papers  (2022-10-27T13:24:08Z)
• Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking [59.79252390626194]
  We propose a novel solution named TransSTAM, which leverages Transformer to model both the appearance features of each object and the spatial-temporal relationships among objects. The proposed method is evaluated on multiple public benchmarks including MOT16, MOT17, and MOT20, and it achieves a clear performance improvement in both IDF1 and HOTA.
  arXiv  Detail & Related papers  (2022-05-31T01:19:18Z)
• Progressive Multi-stage Interactive Training in Mobile Network for Fine-grained Recognition [8.727216421226814]
  We propose a Progressive Multi-Stage Interactive training method with a Recursive Mosaic Generator (RMG-PMSI) First, we propose a Recursive Mosaic Generator (RMG) that generates images with different granularities in different phases. Then, the features of different stages pass through a Multi-Stage Interaction (MSI) module, which strengthens and complements the corresponding features of different stages. Experiments on three prestigious fine-grained benchmarks show that RMG-PMSI can significantly improve the performance with good robustness and transferability.
  arXiv  Detail & Related papers  (2021-12-08T10:50:03Z)
• Convolutional Networks with Dense Connectivity [59.30634544498946]
  We introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks.
  arXiv  Detail & Related papers  (2020-01-08T06:54:53Z)

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.