Publications
(* Equal contribution)
2022
-
With False Friends Like These, Who Can Notice Mistakes?In: AAAI Conference on Artificial Intelligence (AAAI), 2022
2021
-
Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial TrainingIn: Advances in Neural Information Processing Systems (NeurIPS), 2021
-
Open-set Label Noise Can Improve Robustness Against Inherent Label NoiseIn: Advances in Neural Information Processing Systems (NeurIPS), 2021
-
Multiple-Instance Learning from Similar and Dissimilar BagsIn: ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2021
-
Improving Model Robustness by Adaptively Correcting Perturbation Levels with Active QueriesIn: AAAI Conference on Artificial Intelligence (AAAI), 2021
2020
-
Accelerated Stochastic Gradient-free and Projection-free MethodsIn: International Conference on Machine Learning (ICML), 2020
-
Guided CNN for Generalized Zero-shot and Open-set Recognition Using Visual and Semantic PrototypesIn: Pattern Recognition (PR), 2020