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.

本研究提出了一种基于多领域共同学习的新型网络——DKPNet，利用VA技术来显式地建模不同领域之间的注意分布，以及InVA技术来解决领域和子领域重叠的问题，并在ShanghaiTech、UCF-QNRF和NWPU等多个数据集上验证了其优越性。

变分注意力: 用于在人群计数的多领域学习中传播特定于域的知识