Showing cs.CVShow all
2 papers · 1 filter
cs.CV2024
Reducing Spurious Correlation for Federated Domain Generalization
Shuran Ma, Weiying Xie, Daixun Li +2
The rapid development of multimedia has provided a large amount of data with different distributions for visual tasks, forming different domains. Federated Learning (FL) can effici…
cs.CV2023
CurriculumLoc: Enhancing Cross-Domain Geolocalization through Multi-Stage Refinement
Boni Hu, Lin Chen, Runjian Chen +3
Visual geolocalization is a cost-effective and scalable task that involves matching one or more query images, taken at some unknown location, to a set of geo-tagged reference image…