Name: Jingfeng Zhang
Type: User
Company: University of Auckland
Bio: Lecturer (Assistant Professor)@Univ. of Auckland;
Postdoc -> Scientist (2021-23)@RIKEN-AIP, Tokyo; Ph.D. (2016-20)@National University of Singapore
Location: Auckland, New Zealand
Blog: https://scholar.google.com/citations?user=NS0P1FkAAAAJ&hl=en
Jingfeng Zhang's Projects
Challenging label noise called BadLabel; Robust label-noise learning called Robust DivideMix
Attacks Which Do Not Kill Training Make Adversarial Learning Stronger (ICML2020 Paper)
the paper "Geometry-aware Instance-reweighted Adversarial Training" ICLR 2021 oral
Models and examples built with TensorFlow
The code for NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labels (TMLR 22 accept)
Poisoning attack methods against adversarial training algorithms
Towards Robust ResNet: A Small Step but a Giant Leap (IJCAI 2019)
Computation using data flow graphs for scalable machine learning
Demonstration of Transfer Learning on CIFAR10 dataset.
Jingfeng Zhang's personal website