1. Can you trust your model's uncertainty? Evaluating predictive uncertainty under dataset shift;ovadia;NeurIPS,2019
2. Feature visualization;olah;Distillation,2017
3. On interaction between augmentations and corruptions in natural corruption robustness;mintun;ArXiv Preprint,2021
4. Towards deep learning models resistant to adversarial attacks;madry;ICLRE,2018