3 papers
cs.CV2022
Is Synthetic Dataset Reliable for Benchmarking Generalizable Person Re-Identification?
Cuicui Kang
Recent studies show that models trained on synthetic datasets are able to achieve better generalizable person re-identification (GPReID) performance than that trained on public rea…
cs.CV2021
Discovering Spatial Relationships by Transformers for Domain Generalization
Cuicui Kang, Karthik Nandakumar
Due to the rapid increase in the diversity of image data, the problem of domain generalization has received increased attention recently. While domain generalization is a challengi…
cs.CV2020
DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations
Wenhao Wang, Shengcai Liao, Fang Zhao +2
Existing person re-identification models often have low generalizability, which is mostly due to limited availability of large-scale labeled data in training. However, labeling lar…