This paper addresses the tradeoff between standard accuracy on clean exa...
This paper investigates methods for improving generative data augmentati...
Regularized discrete optimal transport (OT) is a powerful tool to measur...
Gate functions in recurrent models, such as an LSTM and GRU, play a cent...
Defending deep neural networks against adversarial examples is a key
cha...
Transfer learning is crucial in training deep neural networks on new tar...
Generative adversarial networks built from deep convolutional neural net...
Deep neural networks are vulnerable to adversarial attacks. Recent studi...
Adversarial training is actively studied for learning robust models agai...
We propose a method for improving adversarial robustness by addition of ...
Self-supervised learning is one of the most promising approaches to lear...
For deep learning applications, the massive data development (e.g.,
coll...
We propose Absum, which is a regularization method for improving adversa...
We propose the Autoencoding Binary Classifiers (ABC), a novel supervised...
Softmax is an output activation function for modeling categorical probab...