Beyond Mamba: Enhancing State-space Models with Deformable Dilated Convolutions for Multi-scale Traffic Object Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908949339439104 |
|---|---|
| author | Li, Jun Shi, Yingying Ruan, Zhixuan Guo, Nan Xu, Jianhua |
| author_facet | Li, Jun Shi, Yingying Ruan, Zhixuan Guo, Nan Xu, Jianhua |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_08038 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Beyond Mamba: Enhancing State-space Models with Deformable Dilated Convolutions for Multi-scale Traffic Object Detection Li, Jun Shi, Yingying Ruan, Zhixuan Guo, Nan Xu, Jianhua Computer Vision and Pattern Recognition 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. |
| title | Beyond Mamba: Enhancing State-space Models with Deformable Dilated Convolutions for Multi-scale Traffic Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.08038 |