Guangtao Zheng

AdvST: Revisiting Data Augmentations for Single Domain Generalization

2023 · arXiv (Cornell University)

Single domain generalization (SDG) aims to train a robust model against unknown target domain shifts using data from a single source domain. Data augmentation has been proven an effective approach to SDG. However, the utility …

ShortcutProbe: Probing Prediction Shortcuts for Learning Robust Models

2024

Deep learning models often achieve high performance by inadvertently learning spurious correlations between targets and non-essential features. For example, an image classifier may identify an object via its background that spuriously correlates with it. This …