Xinhui Liu — accepted AI-conference papers

2024

Attention Shifting to Pursue Optimal Representation for Adapting Multi-granularity Tasks

Gairui Bai, Wei Xi, Yihan Zhao, Xinhui Liu, Jizhong Zhao

IJCAI 2024poster

Object recognition in open environments, e.g., video surveillance, poses significant challenges due to the inclusion of unknown and multi-granularity tasks (MGT). However, recent methods exhibit limitations as they struggle to capture subtle differences between different parts within an object and a…

Cited by 1 Source ↗PDF ↗Scholar ↗

2024

UFDA: Universal Federated Domain Adaptation with Practical Assumptions

Xinhui Liu, Zhenghao Chen, Luping Zhou, Dong Xu, Wei Xi, Gairui Bai +2

AAAI 2024technical

Conventional Federated Domain Adaptation (FDA) approaches usually demand an abundance of assumptions, which makes them significantly less feasible for real-world situations and introduces security hazards. This paper relaxes the assumptions from previous FDAs and studies a more practical scenario na…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗