29 citations · 195 across the 32 of their papers we have counts for
3 papers · 1 filter
How Does Mixup Help With Robustness and Generalization?
Linjun Zhang, Zhun Deng, Kenji Kawaguchi +2
Mixup is a popular data augmentation technique based on taking convex combinations of pairs of examples and their labels. This simple technique has been shown to substantially impr…
Improving Generalization in Meta-learning via Task Augmentation
Huaxiu Yao, Longkai Huang, Linjun Zhang +5
Meta-learning has proven to be a powerful paradigm for transferring the knowledge from previous tasks to facilitate the learning of a novel task. Current dominant algorithms train…
Improving Adversarial Robustness via Unlabeled Out-of-Domain Data
Zhun Deng, Linjun Zhang, Amirata Ghorbani +1
Data augmentation by incorporating cheap unlabeled data from multiple domains is a powerful way to improve prediction especially when there is limited labeled data. In this work, w…