Indirect-Instant Attention Optimization for Crowd Counting in Dense Scenes

06/12/2022
by   Suyu Han, et al.
0

One of appealing approaches to guiding learnable parameter optimization, such as feature maps, is global attention, which enlightens network intelligence at a fraction of the cost. However, its loss calculation process still falls short: 1)We can only produce one-dimensional 'pseudo labels' for attention, since the artificial threshold involved in the procedure is not robust; 2) The attention awaiting loss calculation is necessarily high-dimensional, and decreasing it by convolution will inevitably introduce additional learnable parameters, thus confusing the source of the loss. To this end, we devise a simple but efficient Indirect-Instant Attention Optimization (IIAO) module based on SoftMax-Attention , which transforms high-dimensional attention map into a one-dimensional feature map in the mathematical sense for loss calculation midway through the network, while automatically providing adaptive multi-scale fusion to feature pyramid module. The special transformation yields relatively coarse features and, originally, the predictive fallibility of regions varies by crowd density distribution, so we tailor the Regional Correlation Loss (RCLoss) to retrieve continuous error-prone regions and smooth spatial information . Extensive experiments have proven that our approach surpasses previous SOTA methods in many benchmark datasets.

READ FULL TEXT

page 1

page 3

page 4

page 6

page 9

research
08/07/2019

Attend To Count: Crowd Counting with Adaptive Capacity Multi-scale CNNs

Crowd counting is a challenging task due to the large variations in crow...
research
12/04/2019

Drone-based Joint Density Map Estimation, Localization and Tracking with Space-Time Multi-Scale Attention Network

This paper proposes a space-time multi-scale attention network (STANet) ...
research
11/29/2018

ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding

We propose an attention-injective deformable convolutional network calle...
research
06/27/2018

Attention to Head Locations for Crowd Counting

Occlusions, complex backgrounds, scale variations and non-uniform distri...
research
12/17/2021

Towards More Effective PRM-based Crowd Counting via A Multi-resolution Fusion and Attention Network

The paper focuses on improving the recent plug-and-play patch rescaling ...
research
05/28/2022

Feature Pyramid Attention based Residual Neural Network for Environmental Sound Classification

Environmental sound classification (ESC) is a challenging problem due to...
research
08/02/2017

Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs

We present a novel method called Contextual Pyramid CNN (CP-CNN) for gen...

Please sign up or login with your details

Forgot password? Click here to reset