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

TL;DR

This paper introduces a Hybrid Attention Network (HAN) that combines spatial and channel attention with progressive scale-context embedding to improve crowd counting accuracy by addressing background noise and scale variation simultaneously.

Contribution

The paper proposes a novel hybrid attention mechanism with progressive embedding of scale-context, enabling simultaneous noise suppression and scale adaptation in crowd counting.

Findings

HAN achieves state-of-the-art performance on four datasets.

The hybrid attention mechanism effectively suppresses background noise.

Progressive embedding of scale-context improves scale variation handling.

Abstract

The existing crowd counting methods usually adopted attention mechanism to tackle background noise, or applied multi-level features or multi-scales context fusion to tackle scale variation. However, these approaches deal with these two problems separately. In this paper, we propose a Hybrid Attention Network (HAN) by employing Progressive Embedding Scale-context (PES) information, which enables the network to simultaneously suppress noise and adapt head scale variation. We build the hybrid attention mechanism through paralleling spatial attention and channel attention module, which makes the network to focus more on the human head area and reduce the interference of background objects. Besides, we embed certain scale-context to the hybrid attention along the spatial and channel dimensions for alleviating these counting errors caused by the variation of perspective and head scale. Finally, we propose a progressive learning strategy through cascading multiple hybrid attention modules with embedding different scale-context, which can gradually integrate different scale-context information into the current feature map from global to local. Ablation experiments provides that the network architecture can gradually learn multi-scale features and suppress background noise. Extensive experiments demonstrate that HANet obtain state-of-the-art counting performance on four mainstream datasets.