Multi-scale Feature Aggregation for Crowd Counting

TL;DR

This paper introduces MSFANet, a multi-scale feature aggregation network that effectively addresses scale variation in crowd counting by combining feature fusion modules and local-global counting loss, achieving state-of-the-art results.

Contribution

The paper proposes a novel multi-scale feature aggregation network with two modules and a local-global counting loss to improve crowd counting accuracy under scale variations.

Findings

MSFANet outperforms previous methods on four challenging datasets.

The skip aggregation module effectively fuses features with different receptive fields.

The local-and-global counting loss improves handling of non-uniform crowd distributions.

Abstract

Convolutional Neural Network (CNN) based crowd counting methods have achieved promising results in the past few years. However, the scale variation problem is still a huge challenge for accurate count estimation. In this paper, we propose a multi-scale feature aggregation network (MSFANet) that can alleviate this problem to some extent. Specifically, our approach consists of two feature aggregation modules: the short aggregation (ShortAgg) and the skip aggregation (SkipAgg). The ShortAgg module aggregates the features of the adjacent convolution blocks. Its purpose is to make features with different receptive fields fused gradually from the bottom to the top of the network. The SkipAgg module directly propagates features with small receptive fields to features with much larger receptive fields. Its purpose is to promote the fusion of features with small and large receptive fields. Especially, the SkipAgg module introduces the local self-attention features from the Swin Transformer blocks to incorporate rich spatial information. Furthermore, we present a local-and-global based counting loss by considering the non-uniform crowd distribution. Extensive experiments on four challenging datasets (ShanghaiTech dataset, UCF_CC_50 dataset, UCF-QNRF Dataset, WorldExpo'10 dataset) demonstrate the proposed easy-to-implement MSFANet can achieve promising results when compared with the previous state-of-the-art approaches.