Pedestrian detection plays an important role in many applications such as autonomous driving. We propose a method that explores semantic segmentation results as self-attention cues to significantly improve the pedestrian detection performance. Specifically, a multi-task network is designed to jointly learn semantic segmentation and pedestrian detection from image datasets with weak box-wise annotations. The semantic segmentation feature maps are concatenated with corresponding convolution features maps to provide more discriminative features for pedestrian detection and pedestrian classification. By jointly learning segmentation and detection, our proposed pedestrian self-attention mechanism can effectively identify pedestrian regions and suppress backgrounds. In addition, we propose to incorporate semantic attention information from multi-scale layers into deep convolution neural network to boost pedestrian detection. Experiment results show that the proposed method achieves the best detection performance with MR of 6.27% on Caltech dataset and obtain competitive performance on CityPersons dataset while maintaining high computational efficiency.

本文针对行人检测问题，提出了一种基于语义分割和自注意力机制的多任务网络方法，在弱标注图像数据集上，并入注意力信息，提高了检测性能，在Caltech数据集上达到了MR为6.27%的最佳检测性能，同时在CityPersons数据集上保持高计算效率。

SSA-CNN: 用于行人检测的语义自注意力卷积神经网络