Search Results for author: Yaowei Zheng

Found 4 papers, 3 papers with code

Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentation

2 code implementations21 Jan 2022 Qianben Chen, Richong Zhang, Yaowei Zheng, Yongyi Mao

Contrastive learning has achieved remarkable success in representation learning via self-supervision in unsupervised settings.

Contrastive Learning Data Augmentation +5

Robust Regularization with Adversarial Labelling of Perturbed Samples

no code implementations28 May 2021 Xiaohui Guo, Richong Zhang, Yaowei Zheng, Yongyi Mao

The ALPS regularization objective is formulated as a min-max problem, in which the outer problem is minimizing an upper-bound of the VRM loss, and the inner problem is L$_1$-ball constrained adversarial labelling on perturbed sample.

Adversarial Robustness Computational Efficiency

Regularizing Neural Networks via Adversarial Model Perturbation

1 code implementation CVPR 2021 Yaowei Zheng, Richong Zhang, Yongyi Mao

This work proposes a new regularization scheme, based on the understanding that the flat local minima of the empirical risk cause the model to generalize better.

Image Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.