%Aigaion2 BibTeX export from Idiap Publications
%Wednesday 17 July 2024 05:33:20 PM

@INPROCEEDINGS{Srinivas_NEURALINFORMATIONPROCESSINGSYSTEMS_2019,
         author = {Srinivas, Suraj and Fleuret, Francois},
       projects = {Idiap},
          title = {Full-Gradient Representation for Neural Network Visualization},
      booktitle = {Advances in Neural Information Processing Systems},
           year = {2019},
            url = {https://arxiv.org/abs/1905.00780},
       abstract = {We introduce a new tool for interpreting neural net responses, namely full-gradients,
which decomposes the neural net response into input sensitivity and per-neuron
sensitivity components. This is the first proposed representation which satisfies
two key properties: completeness and weak dependence, which provably cannot
be satisfied by any saliency map-based interpretability method. For convolutional
nets, we also propose an approximate saliency map representation, called FullGrad,
obtained by aggregating the full-gradient components.
We experimentally evaluate the usefulness of FullGrad in explaining model behaviour with two quantitative tests: pixel perturbation and remove-and-retrain.
Our experiments reveal that our method explains model behavior correctly, and
more comprehensively, than other methods in the literature. Visual inspection
also reveals that our saliency maps are sharper and more tightly confined to object
regions than other methods.}
}