ﻻ يوجد ملخص باللغة العربية
We propose a new approach to train a variational information bottleneck (VIB) that improves its robustness to adversarial perturbations. Unlike the traditional methods where the hard labels are usually used for the classification task, we refine the categorical class information in the training phase with soft labels which are obtained from a pre-trained reference neural network and can reflect the likelihood of the original class labels. We also relax the Gaussian posterior assumption in the VIB implementation by using the mutual information neural estimation. Extensive experiments have been performed with the MNIST and CIFAR-10 datasets, and the results show that our proposed approach significantly outperforms the benchmarked models.
Multi-task learning (MTL) is an important subject in machine learning and artificial intelligence. Its applications to computer vision, signal processing, and speech recognition are ubiquitous. Although this subject has attracted considerable attenti
The information bottleneck principle provides an information-theoretic method for representation learning, by training an encoder to retain all information which is relevant for predicting the label while minimizing the amount of other, excess inform
Domain adaptation aims to leverage the supervision signal of source domain to obtain an accurate model for target domain, where the labels are not available. To leverage and adapt the label information from source domain, most existing methods employ
Adversarial learning methods have been proposed for a wide range of applications, but the training of adversarial models can be notoriously unstable. Effectively balancing the performance of the generator and discriminator is critical, since a discri
Compact neural networks are essential for affordable and power efficient deep learning solutions. Binary Neural Networks (BNNs) take compactification to the extreme by constraining both weights and activations to two levels, ${+1, -1}$. However, trai