Preprint

Attention Meets Perturbations: Robust and Interpretable Attention with Adversarial Training

In recent years, deep learning models have placed more emphasis on the interpretability and robustness of models. The attention mechanism is an important technique that contributes to these elements and is widely used, especially in the natural …

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

International Skin Imaging Collaboration 2018.