Recurrent Distillation based Crowd Counting

TL;DR

This paper introduces a perspective-aware density map generation method and an iterative distillation algorithm to improve crowd counting accuracy, achieving state-of-the-art results with a simple CNN architecture.

Contribution

It presents a novel density map generation technique and an iterative distillation process that enhance crowd counting performance without increasing model complexity.

Findings

Outperforms existing methods on various datasets.

Effective density map generation from point annotations.

Iterative distillation improves model accuracy.

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.