S
Shu-Tao Xia
Researcher at Tsinghua University
Publications - 393
Citations - 6305
Shu-Tao Xia is an academic researcher from Tsinghua University. The author has contributed to research in topics: Computer science & Linear code. The author has an hindex of 24, co-authored 322 publications receiving 3350 citations. Previous affiliations of Shu-Tao Xia include Southeast University & Nankai University.
Papers
More filters
Proceedings ArticleDOI
Second-Order Attention Network for Single Image Super-Resolution
TL;DR: Experimental results demonstrate the superiority of the SAN network over state-of-the-art SISR methods in terms of both quantitative metrics and visual quality.
Posted Content
Adversarial Weight Perturbation Helps Robust Generalization
TL;DR: This paper proposes a simple yet effective Adversarial Weight Perturbation (AWP) to explicitly regularize the flatness of weight loss landscape, forming a double-perturbation mechanism in the adversarial training framework that adversarially perturbs both inputs and weights.
Posted Content
Backdoor Learning: A Survey
TL;DR: This paper summarizes and categorizes existing backdoor attacks and defenses based on their characteristics, and provides a unified framework for analyzing poisoning-based backdoor attacks.
Proceedings ArticleDOI
Iterative Learning with Open-set Noisy Labels
TL;DR: In this paper, a Siamese network is proposed to detect noisy labels and learn deep discriminative features in an iterative fashion, and a reweighting module is also applied to simultaneously emphasize the learning from clean labels and reduce the effect caused by noisy labels.
Proceedings Article
Dimensionality-Driven Learning with Noisy Labels
Xingjun Ma,Yisen Wang,Michael E. Houle,Shuo Zhou,Sarah M. Erfani,Shu-Tao Xia,Sudanthi Wijewickrema,James Bailey +7 more
TL;DR: This work proposes a new perspective for understanding DNN generalization for such datasets, by investigating the dimensionality of the deep representation subspace of training samples, and develops a new dimensionality-driven learning strategy that can effectively learn low-dimensional local subspaces that capture the data distribution.