Recurrent Distillation based Crowd Counting

Abstract

In recent years, with the progress of deep learning technologies, crowd counting has been rapidly developed. In this work, we propose a simple yet effective crowd counting framework that is able to achieve the state-of-the-art performance on various crowded scenes. In particular, we first introduce a perspective-aware density map generation method that is able to produce ground-truth density maps from point annotations to train crowd counting model to accomplish superior performance than prior density map generation techniques. Besides, leveraging our density map generation method, we propose an iterative distillation algorithm to progressively enhance our model with identical network structures, without significantly sacrificing the dimension of the output density maps. In experiments, we demonstrate that, with our simple convolutional neural network architecture strengthened by our proposed training algorithm, our model is able to outperform or be comparable with the state-of-the-art methods. Furthermore, we also evaluate our density map generation approach and distillation algorithm in ablation studies.

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distilling the Knowledge in a Neural Network
• Born Again Neural Networks
• CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
• Switching Convolutional Neural Network for Crowd Counting
• Bayesian Loss for Crowd Count Estimation with Point Supervision
• Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds
• Learning from Synthetic Data for Crowd Counting in the Wild
• Crowd Counting with Deep Structured Scale Integration Network
• Perspective-Guided Convolution Networks for Crowd Counting
• From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer
• Learn to Scale: Generating Multipolar Normalized Density Maps for Crowd Counting
• Iterative Crowd Counting
• Learning Spatial Awareness to Improve Crowd Counting