动态Transformer网络提升车辆检测在复杂光照下的适应性。
A Dynamic Transformer Network for Vehicle Detection
- 用动态卷积自适应调整权重，增强模型对环境变化的适应能力。
- 混合注意力机制融合通道与像素关系，提取更显著特征。
- 基于空间位置的变换单元优化结构信息，提升检测精度。
稳定的消费级电子系统可更好地辅助交通管理。理想的交通智能系统需算法与硬件协同工作。然而，现有基于深度网络的车辆检测方法主要依赖数据关联学习，难以应对不同光照和遮挡条件下的性能下降。本文提出一种用于车辆检测的动态Transformer网络（DTNet）。DTNet通过动态卷积引导深度网络动态生成权重，提升检测器的适应性；设计了一种结合通道注意力与Transformer的混合注意力机制，强化通道与像素间的关联，以提取更显著的特征；针对图像表征差异问题，引入依赖空间位置信息的变换单元，精炼结构化信息。实验表明，所提DTNet在车辆检测任务上具有竞争力。代码已开源：https://github.com/hellloxiaotian/DTNet。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。