Making Attention Mechanisms More Robust and Interpretable with Virtual Adversarial Training for Semi-Supervised Text Classification

We propose a new general training technique for attention mechanisms based on virtual adversarial training (VAT). VAT can compute adversarial perturbations from unlabeled data in a semi-supervised setting for the attention mechanisms that have been …

Skin lesion classification with ensemble of squeeze-and-excitation networks and semi-supervised learning

Manuscript for [the International Skin Imaging Collaboration 2018](https://challenge2018.isic-archive.com/).