Xiaoxuan Mu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiaoxuan Mu has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Haitao Shi
School of Mathematics, Physics and Artificial Intelligence, China University of Petroleum–Beijing at Karamay, Karamay 834000, China
1 shared publication - Han Jiang
Xi’an Jiaotong University, Xi’an, China
1 shared publication - Haoyu Tang
School of Software, Shandong University, Jinan, China
1 shared publication - Jihua Zhu
Xi’an Jiaotong University
1 shared publication - Liqiang Nie
Harbin Institute of Technology (Shenzhen), Shenzhen, China
1 shared publication - Qinghai Zheng
Fuzhou University
1 shared publication
Latest Publications
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 4107-4116
FACE: A Dual-Template and Adaptive Curriculum Framework for Unsupervised Text-Based Person Search
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 4107-4116
Open AccessFACE: A Dual-Template and Adaptive Curriculum Framework for Unsupervised Text-Based Person Search
- Open Access
- 19 August 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 42 (6) , 1-26
Breaking Through the Noisy Correspondence: A Robust Model for Image-Text Matching
Unleashing the power of image-text matching in real-world applications is hampered by noisy correspondence. Manually curating high-quality datasets is expensive and time-consuming, and datasets generated using diffusion models are not adequately well-aligned. The most promising way is to collect image-text pairs from the Internet, but it will inevitably introduce noisy correspondence. To reduce the negative impact of noisy correspondence, we propose a novel model that first transforms the noisy correspondence filtering problem into a similarity distribution modeling problem by exploiting the powerful capabilities of pre-trained models. Specifically, we use the Gaussian Mixture model to model the similarity obtained by CLIP as clean distribution and noisy distribution, to filter out most of the noisy correspondence in the dataset. Afterward, we used relatively clean data to fine-tune the model. To further reduce the negative impact of unfiltered noisy correspondence, i.e., a minimal part where two distributions intersect during the fine-tuning process, we propose a distribution-sensitive dynamic margin ranking loss, further increasing the distance between the two distributions. Through continuous iteration, the noisy correspondence gradually decreases and the model performance gradually improves. Our extensive experiments demonstrate the effectiveness and robustness of our model even under high noise rates.
- 19 August 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 42 (6) , 1-26
Open AccessBreaking Through the Noisy Correspondence: A Robust Model for Image-Text Matching
Unleashing the power of image-text matching in real-world applications is hampered by noisy correspondence. Manually curating high-quality datasets is expensive and time-consuming, and datasets generated using diffusion models are not adequately well-aligned. The most promising way is to collect image-text pairs from the Internet, but it will inevitably introduce noisy correspondence. To reduce the negative impact of noisy correspondence, we propose a novel model that first transforms the noisy correspondence filtering problem into a similarity distribution modeling problem by exploiting the powerful capabilities of pre-trained models. Specifically, we use the Gaussian Mixture model to model the similarity obtained by CLIP as clean distribution and noisy distribution, to filter out most of the noisy correspondence in the dataset. Afterward, we used relatively clean data to fine-tune the model. To further reduce the negative impact of unfiltered noisy correspondence, i.e., a minimal part where two distributions intersect during the fine-tuning process, we propose a distribution-sensitive dynamic margin ranking loss, further increasing the distance between the two distributions. Through continuous iteration, the noisy correspondence gradually decreases and the model performance gradually improves. Our extensive experiments demonstrate the effectiveness and robustness of our model even under high noise rates.