Discovering Regression-Detection Bi-knowledge Transfer for Unsupervised Cross-Domain Crowd Counting

Yuting Liu, Zheng Wang, Miaojing Shi, Shin'ichi Satoh, Qijun Zhao, Hongyu Yang

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)
1 Downloads (Pure)


Despite impressive progress in crowd counting over the last years, it is still an open challenge to reliably count crowds across visual domains. This paper addresses this setting, presenting an unsupervised cross-domain crowd counting framework able to perform unsupervised adaptation across domains with available unlabeled target data. We achieve this by learning to discover bi-knowledge transfer between regression- and detection-based models from a labeled source domain. The dual source knowledge of the two models is heterogeneous and complementary as they capture different modalities of crowd distribution. Specifically, we start by formulating the mutual transformations between the outputs of regression- and detection-based models as two scene-agnostic transformers which enable knowledge transfer between the two models. Given the regression- and detection-based models and their mutual transformers learnt on the source, we then introduce a self-supervised co-training scheme to encourage the knowledge transfer between the two models on the target. We further enhance the model adaptation with our modified mixup augmentation strategy. A thorough benchmark analysis against the most recent cross-domain crowd counting methods and detailed ablation studies show the advantage of our method.
Original languageEnglish
Pages (from-to)418-431
Number of pages14
Early online date4 May 2022
Publication statusPublished - 14 Jul 2022


Dive into the research topics of 'Discovering Regression-Detection Bi-knowledge Transfer for Unsupervised Cross-Domain Crowd Counting'. Together they form a unique fingerprint.

Cite this