Scale-Aware Attention Network for Crowd Counting

01/17/2019
by   Rahul Rama Varior, et al.
17

In crowd counting datasets, people appear at different scales, depending on their distance to the camera. To address this issue, we propose a novel multi-branch scale-aware attention network that exploits the hierarchical structure of convolutional neural networks and generates, in a single forward pass, multi-scale density predictions from different layers of the architecture. To aggregate these maps into our final prediction, we present a new soft attention mechanism that learns a set of gating masks. Furthermore, we introduce a scale-aware loss function to regularize the training of different branches and guide them to specialize on a particular scale. As this new training requires ground-truth annotations for the size of each head, we also propose a simple, yet effective technique to estimate it automatically. Finally, we present an ablation study on each of these components and compare our approach against the literature on 4 crowd counting datasets: UCF-QNRF, ShanghaiTech A & B and UCF_CC_50. Without bells and whistles, our approach achieves state-of-the-art on all these datasets. We observe a remarkable improvement on the UCF-QNRF (25 10

READ FULL TEXT

page 1

page 3

page 6

page 7

page 8

research
03/05/2019

Crowd Counting Using Scale-Aware Attention Networks

In this paper, we consider the problem of crowd counting in images. Give...
research
02/04/2019

Dual Path Multi-Scale Fusion Networks with Attention for Crowd Counting

The task of crowd counting in varying density scenes is an extremely dif...
research
08/04/2022

Redesigning Multi-Scale Neural Network for Crowd Counting

Perspective distortions and crowd variations make crowd counting a chall...
research
06/04/2021

Hybrid attention network based on progressive embedding scale-context for crowd counting

The existing crowd counting methods usually adopted attention mechanism ...
research
08/18/2021

Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting

In crowd counting, due to the problem of laborious labelling, it is perc...
research
08/22/2018

Stacked Pooling: Improving Crowd Counting by Boosting Scale Invariance

In this work, we explore the cross-scale similarity in crowd counting sc...
research
07/24/2019

HA-CCN: Hierarchical Attention-based Crowd Counting Network

Single image-based crowd counting has recently witnessed increased focus...

Please sign up or login with your details

Forgot password? Click here to reset