Beyond Mamba: Enhancing State-space Models with Deformable Dilated Convolutions for Multi-scale Traffic Object Detection

• URL: http://arxiv.org/abs/2604.08038v1
• Date: Thu, 09 Apr 2026 09:43:00 GMT
• Title: Beyond Mamba: Enhancing State-space Models with Deformable Dilated Convolutions for Multi-scale Traffic Object Detection
• Abstract summary: We propose a Mamba with Deformable Dilated Convolutions Network (MDDCNet) for accurate traffic object detection in this study.<n>In MDDCNet, a well-designed hybrid backbone with successive Mamba blocks enables hierarchical feature representation from local details to global semantics.<n>A Channel-Enhanced Feed-Forward Network (CE-FFN) is further devised to overcome the limited channel interaction capability of conventional feed-forward networks.
• Score: 6.929321171294922
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In a real-world traffic scenario, varying-scale objects are usually distributed in a cluttered background, which poses great challenges to accurate detection. Although current Mamba-based methods can efficiently model long-range dependencies, they still struggle to capture small objects with abundant local details, which hinders joint modeling of local structures and global semantics. Moreover, state-space models exhibit limited hierarchical feature representation and weak cross-scale interaction due to flat sequential modeling and insufficient spatial inductive biases, leading to sub-optimal performance in complex scenes. To address these issues, we propose a Mamba with Deformable Dilated Convolutions Network (MDDCNet) for accurate traffic object detection in this study. In MDDCNet, a well-designed hybrid backbone with successive Multi-Scale Deformable Dilated Convolution (MSDDC) blocks and Mamba blocks enables hierarchical feature representation from local details to global semantics. Meanwhile, a Channel-Enhanced Feed-Forward Network (CE-FFN) is further devised to overcome the limited channel interaction capability of conventional feed-forward networks, whilst a Mamba-based Attention-Aggregating Feature Pyramid Network (A^2FPN) is constructed to achieve enhanced multi-scale feature fusion and interaction. Extensive experimental results on public benchmark and real-world datasets demonstrate the superiority of our method over various advanced detectors. The code is available at https://github.com/Bettermea/MDDCNet.

Related papers

• Samba+: General and Accurate Salient Object Detection via A More Unified Mamba-based Framework [66.2103745798444]
  Saliency Mamba (Samba) is a pure Mamba-based architecture that flexibly handles various distinct salient object detection tasks.<n>Samba individually outperforms existing methods across six SOD tasks on 22 datasets with lower computational cost.<n>Samba+ achieves even superior results on these tasks and datasets by using a single trained versatile model.
  arXiv  Detail & Related papers  (2026-02-02T03:34:25Z)
• M2I2HA: Multi-modal Object Detection Based on Intra- and Inter-Modal Hypergraph Attention [5.485819352754784]
  We propose a multi-modal perception network based on hypergraph theory called M2I2HA.<n>Our architecture includes an Intra-Hypergraph Enhancement module to capture global many-to-many high-order relationships within each modality.<n>An Inter-Hypergraph Fusion module to align, enhance, and fuse cross-modal features by bridging configuration and spatial gaps between data sources.
  arXiv  Detail & Related papers  (2026-01-21T08:55:07Z)
• TSkel-Mamba: Temporal Dynamic Modeling via State Space Model for Human Skeleton-based Action Recognition [59.99922360648663]
  TSkel-Mamba is a hybrid Transformer-Mamba framework that effectively captures both spatial and temporal dynamics.<n>The MTI module employs multi-scale Cycle operators to capture cross-channel temporal interactions, a critical factor in action recognition.
  arXiv  Detail & Related papers  (2025-12-12T11:55:16Z)
• MambaTAD: When State-Space Models Meet Long-Range Temporal Action Detection [94.12444452690329]
  This paper presents MambaTAD, a new state-space TAD model that introduces long-range modeling and global feature detection capabilities.<n>MambaTAD achieves superior TAD performance consistently across multiple public benchmarks.
  arXiv  Detail & Related papers  (2025-11-22T06:04:29Z)
• CSFMamba: Cross State Fusion Mamba Operator for Multimodal Remote Sensing Image Classification [12.959829835589453]
  We propose Cross State Fusion Mamba (Camba) Network.<n>Specifically, we first design the preprocessing module of remote sensing image information for the needs of Mamba structure.<n> Secondly, a cross-state module based on Mamba operator is creatively designed to fully fuse the feature of the two modalities.
  arXiv  Detail & Related papers  (2025-08-31T03:08:34Z)
• GCRPNet: Graph-Enhanced Contextual and Regional Perception Network for Salient Object Detection in Optical Remote Sensing Images [68.33481681452675]
  We propose a graph-enhanced contextual and regional perception network (GCRPNet)<n>It builds upon the Mamba architecture to simultaneously capture long-range dependencies and enhance regional feature representation.<n>It performs adaptive patch scanning on feature maps processed via multi-scale convolutions, thereby capturing rich local region information.
  arXiv  Detail & Related papers  (2025-08-14T11:31:43Z)
• AtrousMamaba: An Atrous-Window Scanning Visual State Space Model for Remote Sensing Change Detection [29.004019252136565]
  We propose a novel model, AtrousMamba, which balances the extraction of fine-grained local details with the integration of global contextual information.<n>By leveraging the atrous window scan visual state space (AWVSS) module, we design dedicated end-to-end Mamba-based frameworks for binary change detection (BCD) and semantic change detection (SCD)<n> Experimental results on six benchmark datasets show that the proposed framework outperforms existing CNN-based, Transformer-based, and Mamba-based methods.
  arXiv  Detail & Related papers  (2025-07-22T02:36:16Z)
• InceptionMamba: An Efficient Hybrid Network with Large Band Convolution and Bottleneck Mamba [21.47782205082816]
  InceptionNeXt has shown excellent competitiveness in image classification and a number of downstream tasks.<n>Built on parallel one-dimensional strip convolutions, InceptionNeXt suffers from limited ability of capturing spatial dependencies along different dimensions.<n>We propose a novel backbone architecture termed InceptionMamba to overcome these limitations.
  arXiv  Detail & Related papers  (2025-06-10T12:31:05Z)
• MDDFNet: Mamba-based Dynamic Dual Fusion Network for Traffic Sign Detection [0.081585306387285]
  We propose a novel object detection network, Mamba-based Dynamic Dual Fusion Network (MDDFNet) for traffic sign detection.<n>The network integrates a dynamic dual fusion module and a Mamba-based backbone to simultaneously tackle the aforementioned issues.<n>Extensive experiments conducted on the TT100K (Tsinghua-Tencent 100K) datasets demonstrate that MDDFNet outperforms other state-of-the-art detectors.
  arXiv  Detail & Related papers  (2025-05-02T14:53:25Z)
• VRS-UIE: Value-Driven Reordering Scanning for Underwater Image Enhancement [104.78586859995333]
  State Space Models (SSMs) have emerged as a promising backbone for vision tasks due to their linear complexity and global receptive field.<n>The predominance of large-portion, homogeneous but useless oceanic backgrounds can dilute the feature representation responses of sparse yet valuable targets.<n>We propose a novel Value-Driven Reordering Scanning framework for Underwater Image Enhancement (UIE)<n>Our framework sets a new state-of-the-art, delivering superior enhancement performance (surpassing WMamba by 0.89 dB on average) by effectively suppressing water bias and preserving structural and color fidelity.
  arXiv  Detail & Related papers  (2025-05-02T12:21:44Z)
• LaMamba-Diff: Linear-Time High-Fidelity Diffusion Models Based on Local Attention and Mamba [54.85262314960038]
  Local Attentional Mamba blocks capture both global contexts and local details with linear complexity. Our model exhibits exceptional scalability and surpasses the performance of DiT across various model scales on ImageNet at 256x256 resolution. Compared to state-of-the-art diffusion models on ImageNet 256x256 and 512x512, our largest model presents notable advantages, such as a reduction of up to 62% GFLOPs.
  arXiv  Detail & Related papers  (2024-08-05T16:39:39Z)

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.