Stacked Pooling: Improving Crowd Counting by Boosting Scale Invariance

Abstract

In this work, we explore the cross-scale similarity in crowd counting scenario, in which the regions of different scales often exhibit high visual similarity. This feature is universal both within an image and across different images, indicating the importance of scale invariance of a crowd counting model. Motivated by this, in this paper we propose simple but effective variants of pooling module, i.e., multi-kernel pooling and stacked pooling, to boost the scale invariance of convolutional neural networks (CNNs), benefiting much the crowd density estimation and counting. Specifically, the multi-kernel pooling comprises of pooling kernels with multiple receptive fields to capture the responses at multi-scale local ranges. The stacked pooling is an equivalent form of multi-kernel pooling, while, it reduces considerable computing cost. Our proposed pooling modules do not introduce extra parameters into model and can easily take place of the vanilla pooling layer in implementation. In empirical study on two benchmark crowd counting datasets, the stacked pooling beats the vanilla pooling layer in most cases.

arXiv commentThe code is available at http://github.com/siyuhuang/crowdcount-stackpool

References in corpus (7)

• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• Stochastic Pooling for Regularization of Deep Convolutional Neural Networks
• CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
• Scale-Invariant Convolutional Neural Networks
• Switching Convolutional Neural Network for Crowd Counting
• Multi-scale Convolutional Neural Networks for Crowd Counting
• Structured Inhomogeneous Density Map Learning for Crowd Counting

Cited by in corpus (8)

• Drone-based Joint Density Map Estimation, Localization and Tracking with Space-Time Multi-Scale Attention Network
• Learning Spatial Awareness to Improve Crowd Counting
• BBA-net: A bi-branch attention network for crowd counting
• Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark
• NAS-Count: Counting-by-Density with Neural Architecture Search
• Improving the Learning of Multi-column Convolutional Neural Network for Crowd Counting
• Learning scale-variant features for robust iris authentication with deep learning based ensemble framework
• Mask-aware networks for crowd counting