Pedestrian attribute recognition (PAR) aims to identify the attributes like gender, hat, and upper clothes color of a captured pedestrian, which is a challenging but practical research problem in security applications. One key consideration in PAR is that the uniform extracted features of the backbone cannot effectively fulfill the requirements for classifying each attribute. In the scope of the MMVRAC challenge, this paper introduces the Attribute-aware Multi-layer Projector (AMLP) to enhance the performance in the UAVHuman pedestrian attribute recognition benchmark. The AMLP transforms the uniform pedestrian feature into attribute-aware representation, thereby enhancing the subsequent prediction accuracy. Furthermore, we validate the validity of the AMLP and develop a strong pipeline for PAR based on sufficient experiments, which validates the effectiveness of various commonly employed modules used to improve PAR, such as data augmentation, label smoothing or dropout.
原文链接
分享
引用
