1. Deep inside convolutional networks: visualising image classification models and saliency maps;simonyan;Proceedings of the International Conference on Learning Representations,0
2. Estimating informativeness of samples with smooth unique information;harutyunyan;Proceedings of the International Conference on Learning Representations,0
3. Understanding inter-locking dynamics of cooperative rationalization;yu;Proceedings of the Annual Conference on Neural Information Processing Systems,0
4. Understanding black-box predictions via influence functions;koh;Proceedings of the International Conference on Machine Learning,0
5. Axiomatic attribution for deep networks;sundararajan;Proceedings of the International Conference on Machine Learning,0