Wu Chen

Wu Chen

Auto-generated profile, based on publicly available information

Wu Chen

Southwest University, China

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 March 2021 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
ZWZhi Wang
Zhi Wang
YLYu Liu
Yu Liu
XWXin DI WU
Xin DI WU
Jianjun WangJianjun Wang
Jianjun Wang
Chao GaoChao Gao
Chao Gao
WCWu Chen
Wu Chen
Low-rank minimization aims to recover a matrix of minimum rank subject to linear system constraint. It can be found in various data analysis and machine learning areas, such as recommender systems, video denoising, and signal processing. Nuclear norm minimization is a dominating approach to handle it. However, such a method ignores the difference among singular values of target matrix. To address this issue, nonconvex low-rank regularizers have been widely used. Unfortunately, existing methods suffer from different drawbacks, such as inefficiency and inaccuracy. To alleviate such problems, this article proposes a flexible model with a novel nonconvex regularizer. Such a model not only promotes low rankness but also can be solved much faster and more accurate. With it, the original low-rank problem can be equivalently transformed into the resulting optimization problem under the rank restricted isometry property (rank-RIP) condition. Subsequently, Nesterov’s rule and inexact proximal strategies are adopted to achieve a novel algorithm highly efficient in solving this problem at a convergence rate of $O(1/K)$ , with $K$ being the iterate count. Besides, the asymptotic convergence rate is also analyzed rigorously by adopting the Kurdyka- ojasiewicz (KL) inequality. Furthermore, we apply the proposed optimization model to typical low-rank problems, including matrix completion, robust principal component analysis (RPCA), and tensor completion. Exhaustively empirical studies regarding data analysis tasks, i.e., synthetic data analysis, image recovery, personalized recommendation, and background subtraction, indicate that the proposed model outperforms state-of-the-art models in both accuracy and efficiency.

17 April 2020 in International Journal of Machine Learning and Cybernetics
Verified
Journal Article
Closed access
PDF file
ZWZhi Wang
Zhi Wang
CGChao Gao
Chao Gao
XLXiaohu Luo
Xiaohu Luo
MTMing Tang
Ming Tang
Jianjun WangJianjun Wang
Jianjun Wang
WCWu Chen
Wu Chen

29 June 2021 in International Journal of Machine Learning and Cybernetics
Verified
Journal Article
Closed access
PDF file
ZWZhi Wang
Zhi Wang
DHDong Hu
Dong Hu
XLXiaohu Luo
Xiaohu Luo
WWWendong Wang
Wendong Wang
Jianjun WangJianjun Wang
Jianjun Wang
WCWu Chen
Wu Chen

27 May 2024 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
Jianping GouJianping Gou
Jianping Gou
XZXiabin Zhou
Xiabin Zhou
LDLan Du
Lan Du
YZYibing Zhan
Yibing Zhan
WCWu Chen
Wu Chen
ZYZhang Yi
Zhang Yi
In recent years, various distillation methods for semantic segmentation have been proposed. However, these methods typically train the student model to imitate the intermediate features or logits of the teacher model directly, thereby overlooking the high-discrepancy regions learned by both models, particularly the differences in instance edges. In this paper, we introduce a novel approach, called Difference-aware Distillation, to address this limitation. Our proposed method detects the discrepancies among the teacher model and the student model in the logit space through two masking mechanisms (i.e., masking by logit differences with respect to the ground truth labels and masking by differences in the predictive class probabilities), and guides the student model to restore the teacher's features with the focus on these highly-discrepant regions, resulting in improved segmentation performance. With the features jointly masked by these two mechanisms, the student model learns to preserve the teacher's features via a feature generation module, thus achieving better representation. Our experimental evaluation on three datasets, Cityscapes, Pascal2012, and ADE20 K, demonstrates our proposed approach outperforms several baselines considered. Further visualization analysis confirms that our method effectively directs the student model's attention to the discrepancies, such as the edges of small objects and the interiors of large objects.

26 May 2023 in Proceedings of the ACM on Management of Data
Verified
Journal Article
Open access
ZZZhuoxing Zhang
Zhuoxing Zhang
WCWu Chen
Wu Chen
SLSebastian Link
Sebastian Link
We parameterize schemata in Boyce-Codd Normal Form (BCNF) by the number n of minimal keys they exhibit. We show that n quantifies a trade-off between access variety and update complexity. Indeed, access variety refers to the number of different ways by which every entity over the schema is represented uniquely, while update complexity refers to the number of attribute sets for which uniqueness needs to be preserved during updates. As normalization aims at minimizing the level of effort required to preserve data consistency during updates, we establish an algorithm that returns a lossless, dependency-preserving 3NF decomposition where the subset of output schemata not in BCNF is minimized and redundant BCNF schemata are eliminated from the highest to the lowest n exhibited. In particular, if a lossless, dependency-preserving BCNF decomposition exists, our algorithm returns one where the maximum n across all output schemata is minimized. Experiments with synthetic and real-world data quantify the impact of n on the update and query performance over schemata in BCNF with n minimal keys, and show insight into the efficacy of our algorithm suite.

15 December 2023
Verified
Book Chapter
Closed access
PDF file
ZHZhangyue He
Zhangyue He
YTYanni Tang
Yanni Tang
KZKaiqi Zhao
Kaiqi Zhao
JLJiamou Liu
Jiamou Liu
WCWu Chen
Wu Chen