Model Releases
Beyond Mamba: Enhancing State-space Models with Deformable Dilated Convolutions for Multi-scale Traffic Object Detection
arXiv:2604.08038v1 Announce Type: new Abstract: In a real-world traffic scenario, varying-scale objects are usually distributed in a cluttered background, which poses great challenges to accurate dete
arXiv:2604.08038v1 Announce Type: new 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
- CAMotion: A High-Quality Benchmark for Camouflaged Moving Object Detection in the Wild
- Adaptive Depth-converted-Scale Convolution for Self-supervised Monocular Depth Estimation
- Orion-Lite: Distilling LLM Reasoning into Efficient Vision-Only Driving Models
- CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and Reasoning
- ESOM: Efficiently Understanding Streaming Video Anomalies with Open-world Dynamic Definitions
Source: arXiv cs.CV | 2026-04-10