Performance-enhancing network pruning for crowd counting

LeCun, 2015, Deep learning, Nature, 521, 436, 10.1038/nature14539 Gao, 2016, People counting based on head detection combining adaboost and CNN in crowded surveillance environment, Neurocomputing, 208, 108, 10.1016/j.neucom.2016.01.097 Redmon, 2018 He, 2017, Mask R-CNN, 2980 Sindagi, 2018, A survey of recent advances in CNN-based single image crowd counting and density estimation, Pattern Recognit. Lett., 107, 3, 10.1016/j.patrec.2017.07.007 Onoro-Rubio, 2016, Towards perspective-free object counting with deep learning, 615 Sam, 2017, Switching convolutional neural network for crowd counting, 1, 6 Kumagai, 2017 Zeng, 2017, Multi-scale convolutional neural networks for crowd counting, 465 Cheng, 2017 Molchanov, 2016 Li, 2016, Pruning filters for efficient convnets Han, 2015, Deep compression: compressing deep neural networks with pruning, trained quantization and Huffman coding Li, 2018, CSRNet: dilated convolutional neural networks for understanding the highly congested scenes, 1091 Srinivas, 2015 Ullrich, 2017 Zeiler, 2014, Visualizing and understanding convolutional networks, 818 Arteta, 2014, Interactive object counting, 504 Idrees, 2013, Multi-source multi-scale counting in extremely dense crowd images, 2547 Chan, 2008, Privacy preserving crowd monitoring: counting people without people models or tracking, 1 Zhang, 2016, Single-image crowd counting via multi-column convolutional neural network, 589 Guerrero-Gómez-Olmedo, 2015, Extremely overlapping vehicle counting, 423 Shang, 2016, End-to-end crowd counting via joint learning local and global count, 1215 Luo, 2017, Thinet: a filter level pruning method for deep neural network compression Hinton, 2015