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 language | English |
---|---|
Title of host publication | Proceedings of the 37th AAAI Conference on Artificial Intelligence |
Editors | B. Williams, Y. Chen, J. Neville |
Publisher | Association for the Advancement of Artificial Intelligence |
Pages | 561-570 |
Number of pages | 10 |
Volume | 37 |
Edition | 1 |
ISBN (Electronic) | 9781577358800 |
DOIs | |
Publication status | Published - 26 Jun 2023 |
Event | The Thirty-Seventh AAAI Conference on Artificial Intelligence - Washington Convention Center, Washington, D.C., United States Duration: 7 Feb 2023 → 14 Feb 2023 https://aaai-23.aaai.org/ |
Publication series
Name | Proceedings of the AAAI Conference on Artificial Intelligence |
---|---|
Publisher | Association for the Advancement of Artificial Intelligence |
ISSN (Print) | 2159-5399 |
ISSN (Electronic) | 2374-3468 |
Conference
Conference | The Thirty-Seventh AAAI Conference on Artificial Intelligence |
---|---|
Abbreviated title | AAAI-23 |
Country/Territory | United States |
City | Washington, D.C. |
Period | 7/02/23 → 14/02/23 |
Internet address |