Huiyu Jiang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Interests
Huiyu Jiang has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Xiao Luo
University of Wisconsin–Madison, Madison, WI, USA
2 shared publications - Carl Yang
Emory University
1 shared publication - Chong Chen
Hesicare Technology Co. Ltd, Shanghai, China
1 shared publication - Haixin Wang
University of California, Los Angeles, Los Angeles, CA, USA
1 shared publication - Hang Zhou
University of California, Davis, Davis, CA, USA
1 shared publication - Jinan Sun
National Engineering Research Center for Software Engineering, Peking University, Beijing 100871, China
1 shared publication
Latest Publications
- Open Access
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 906-917
Future Matters for Present: Towards Effective Physical Simulation over Meshes
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 906-917
Open AccessFuture Matters for Present: Towards Effective Physical Simulation over Meshes
- 5 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (4) , 1502-1517
DIOR: Learning to Hash With Label Noise Via Dual Partition and Contrastive Learning
Due to the excellent computing efficiency, learning to hash has acquired broad popularity for Big Data retrieval. Although supervised hashing methods have achieved promising performance recently, they presume that all training samples are appropriately annotated. Unfortunately, label noise is ubiquitous owing to erroneous annotations in real-world applications, which could seriously deteriorate the retrieval performance due to imprecise supervised guidance and severe memorization of noisy data. Here we propose a comprehensive method DIOR to handle the difficulties of learning to hash with label noise. DIOR performs partitions from two complementary levels, namely sample level and parameter level. On the one hand, DIOR divides the dataset into a labeled set with clean samples and an unlabeled set with noisy samples using an ensemble of perturbed views. Then we train the network in a contrastive semi-supervised manner by reconstructing label embeddings for both reliable supervision of clean data and sufficient exploration of noisy data. On the other hand, inspired by recent pruning techniques, DIOR divides the parameters in the hashing network into crucial parameters and non-crucial parameters, and then optimizes them separately to reduce the overfitting of noisy data. Extensive experiments on four popular benchmark datasets demonstrate the effectiveness of DIOR.
- 5 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (4) , 1502-1517
DIOR: Learning to Hash With Label Noise Via Dual Partition and Contrastive Learning
Due to the excellent computing efficiency, learning to hash has acquired broad popularity for Big Data retrieval. Although supervised hashing methods have achieved promising performance recently, they presume that all training samples are appropriately annotated. Unfortunately, label noise is ubiquitous owing to erroneous annotations in real-world applications, which could seriously deteriorate the retrieval performance due to imprecise supervised guidance and severe memorization of noisy data. Here we propose a comprehensive method DIOR to handle the difficulties of learning to hash with label noise. DIOR performs partitions from two complementary levels, namely sample level and parameter level. On the one hand, DIOR divides the dataset into a labeled set with clean samples and an unlabeled set with noisy samples using an ensemble of perturbed views. Then we train the network in a contrastive semi-supervised manner by reconstructing label embeddings for both reliable supervision of clean data and sufficient exploration of noisy data. On the other hand, inspired by recent pruning techniques, DIOR divides the parameters in the hashing network into crucial parameters and non-crucial parameters, and then optimizes them separately to reduce the overfitting of noisy data. Extensive experiments on four popular benchmark datasets demonstrate the effectiveness of DIOR.