XitingLiu — accepted AI-conference papers

2025

Deep Unsupervised Hashing via External Guidance

Qihong Song, XitingLiu, Hongyuan Zhu, Joey Tianyi Zhou, Xi Peng, Peng Hu

ICML 2025poster

Recently, deep unsupervised hashing has gained considerable attention in image retrieval due to its advantages in cost-free data labeling, computational efficiency, and storage savings. Although existing methods achieve promising performance by leveraging inherent visual structures within the data,…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Test-time Adaptation for Cross-modal Retrieval with Query Shift

Haobin Li, Peng Hu, Qianjun Zhang, Xi Peng, XitingLiu, Mouxing Yang

ICLR 2025spotlight

The success of most existing cross-modal retrieval methods heavily relies on the assumption that the given queries follow the same distribution of the source domain. However, such an assumption is easily violated in real-world scenarios due to the complexity and diversity of queries, thus leading t…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗