Towards better understanding of gradient-based attribution methods for Deep Neural Networks
Towards better understanding of gradient-based attribution methods for Deep Neural Networks
Marco Ancona,Enea Ceolini,Cengiz Öztireli,Markus H. Gross
2017 · DOI: 10.3929/ETHZ-B-000249929
International Conference on Learning Representations · 1,027 Citations
TLDR
This work analyzes four gradient-based attribution methods and formally prove conditions of equivalence and approximation between them, and constructs a unified framework which enables a direct comparison, as well as an easier implementation.