Domain-general crowd counting in unseen scenarios

Zhipeng Du, Jiankang Deng, Miaojing Shi*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Domain shift across crowd data severely hinders crowd counting models to generalize to unseen scenarios. Although domain adaptive crowd counting approaches close this gap to a certain extent, they are still dependent on the target domain data to adapt (e.g. finetune) their models to the specific domain. In this paper, we aim to train a model based on a single source domain which can generalize well on any unseen domain. This falls into the realm of domain generalization that remains unexplored in crowd counting. We first introduce a dynamic sub-domain division scheme which divides the source domain into multiple sub-domains such that we can initiate a meta-learning framework for domain generalization. The sub-domain division is dynamically refined during the meta-learning. Next, in order to disentangle domain-invariant information from domain-specific information in image features, we design the domain-invariant and -specific crowd memory modules to re-encode image features. Two types of losses, i.e. feature reconstruction and orthogonal losses, are devised to enable this disentanglement. Extensive experiments on several standard crowd counting benchmarks i.e. SHA, SHB, QNRF, and NWPU, show the strong generalizability of our method.
Original languageEnglish
Title of host publicationProceedings of the 37th AAAI Conference on Artificial Intelligence
EditorsB. Williams, Y. Chen, J. Neville
PublisherAssociation for the Advancement of Artificial Intelligence
Pages561-570
Number of pages10
Volume37
Edition1
ISBN (Electronic)9781577358800
DOIs
Publication statusPublished - 26 Jun 2023
EventThe Thirty-Seventh AAAI Conference on Artificial Intelligence - Washington Convention Center, Washington, D.C., United States
Duration: 7 Feb 202314 Feb 2023
https://aaai-23.aaai.org/

Publication series

NameProceedings of the AAAI Conference on Artificial Intelligence
PublisherAssociation for the Advancement of Artificial Intelligence
ISSN (Print)2159-5399
ISSN (Electronic)2374-3468

Conference

ConferenceThe Thirty-Seventh AAAI Conference on Artificial Intelligence
Abbreviated titleAAAI-23
Country/TerritoryUnited States
CityWashington, D.C.
Period7/02/2314/02/23
Internet address

Fingerprint

Dive into the research topics of 'Domain-general crowd counting in unseen scenarios'. Together they form a unique fingerprint.

Cite this