Yuxuan Gu, Meng Wu*, Qian Wang, Siguang Chen, Lijun Yang
CMC-Computers, Materials & Continua, Vol.75, No.1, pp. 493-512, 2023, DOI:10.32604/cmc.2023.035974
Abstract In this paper, a deep learning-based method is proposed for crowd-counting problems. Specifically, by utilizing the convolution kernel density map, the ground truth is generated dynamically to enhance the feature-extracting ability of the generator model. Meanwhile, the “cross stage partial” module is integrated into congested scene recognition network (CSRNet) to obtain a lightweight network model. In addition, to compensate for the accuracy drop owing to the lightweight model, we take advantage of “structured knowledge transfer” to train the model in an end-to-end manner. It aims to accelerate the fitting speed and enhance the learning ability of the student model. The… More >
Login
Register
