A Dynamic Transformer Network for Vehicle Detection

TL;DR

This paper introduces DTNet, a dynamic Transformer-based network that improves vehicle detection by adaptively focusing on salient features through dynamic convolution and mixed attention mechanisms, addressing lighting and occlusion challenges.

Contribution

The paper proposes a novel DTNet architecture combining dynamic convolution and mixed attention to enhance vehicle detection under varying conditions.

Findings

DTNet achieves competitive detection accuracy.

Dynamic convolution improves adaptability to lighting and occlusion.

Mixed attention strengthens feature extraction.

Abstract

Stable consumer electronic systems can assist traffic better. Good traffic consumer electronic systems require collaborative work between traffic algorithms and hardware. However, performance of popular traffic algorithms containing vehicle detection methods based on deep networks via learning data relation rather than learning differences in different lighting and occlusions is limited. In this paper, we present a dynamic Transformer network for vehicle detection (DTNet). DTNet utilizes a dynamic convolution to guide a deep network to dynamically generate weights to enhance adaptability of an obtained detector. Taking into relations of different information account, a mixed attention mechanism based channel attention and Transformer is exploited to strengthen relations of channels and pixels to extract more salient information for vehicle detection. To overcome the drawback of difference in an image account, a translation-variant convolution relies on spatial location information to refine obtained structural information for vehicle detection. Experimental results illustrate that our DTNet is competitive for vehicle detection. Code of the proposed DTNet can be obtained at https://github.com/hellloxiaotian/DTNet.