2 papers
cs.LG2020
Adversarial Examples Detection and Analysis with Layer-wise Autoencoders
Bartosz Wójcik, Paweł Morawiecki, Marek Śmieja +3
We present a mechanism for detecting adversarial examples based on data representations taken from the hidden layers of the target network. For this purpose, we train individual au…
cs.LG2020
Finding the Optimal Network Depth in Classification Tasks
Bartosz Wójcik, Maciej Wołczyk, Klaudia Bałazy +1
We develop a fast end-to-end method for training lightweight neural networks using multiple classifier heads. By allowing the model to determine the importance of each head and rew…