HDNet: A Hierarchically Decoupled Network for Crowd Counting

TL;DR

HDNet introduces a hierarchical decoupling approach for crowd counting that separates background and foreground tasks, employing specialized modules and interaction strategies to improve density map prediction accuracy.

Contribution

The paper proposes a novel Hierarchically Decoupled Network (HDNet) that effectively separates background and foreground density estimation tasks with interaction mechanisms, achieving state-of-the-art results.

Findings

HDNet outperforms existing methods on multiple benchmarks.

Hierarchical decoupling reduces hypothesis space and improves optimization.

Interaction strategies enhance task cooperation and accuracy.

Abstract

Recently, density map regression-based methods have dominated in crowd counting owing to their excellent fitting ability on density distribution. However, further improvement tends to saturate mainly because of the confusing background noise and the large density variation. In this paper, we propose a Hierarchically Decoupled Network (HDNet) to solve the above two problems within a unified framework. Specifically, a background classification sub-task is decomposed from the density map prediction task, which is then assigned to a Density Decoupling Module (DDM) to exploit its highly discriminative ability. For the remaining foreground prediction sub-task, it is further hierarchically decomposed to several density-specific sub-tasks by the DDM, which are then solved by the regression-based experts in a Foreground Density Estimation Module (FDEM). Although the proposed strategy effectively reduces the hypothesis space so as to relieve the optimization for those task-specific experts, the high correlation of these sub-tasks are ignored. Therefore, we introduce three types of interaction strategies to unify the whole framework, which are Feature Interaction, Gradient Interaction, and Scale Interaction. Integrated with the above spirits, HDNet achieves state-of-the-art performance on several popular counting benchmarks.