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

TL;DR

This paper introduces DKPNet, a multi-domain crowd counting model that uses Variational Attention to effectively learn from diverse datasets, improving accuracy across multiple benchmarks.

Contribution

The paper proposes a novel Variational Attention technique and an extension, InVA, for multi-domain learning in crowd counting, addressing domain overlap and diversity issues.

Findings

DKPNet outperforms existing methods on multiple datasets.

Variational Attention effectively models domain-specific knowledge.

InVA handles overlapping domains and sub-domains successfully.

Abstract

In crowd counting, due to the problem of laborious labelling, it is perceived intractability of collecting a new large-scale dataset which has plentiful images with large diversity in density, scene, etc. Thus, for learning a general model, training with data from multiple different datasets might be a remedy and be of great value. In this paper, we resort to the multi-domain joint learning and propose a simple but effective Domain-specific Knowledge Propagating Network (DKPNet)1 for unbiasedly learning the knowledge from multiple diverse data domains at the same time. It is mainly achieved by proposing the novel Variational Attention(VA) technique for explicitly modeling the attention distributions for different domains. And as an extension to VA, Intrinsic Variational Attention(InVA) is proposed to handle the problems of over-lapped domains and sub-domains. Extensive experiments have been conducted to validate the superiority of our DKPNet over several popular datasets, including ShanghaiTech A/B, UCF-QNRF and NWPU.