Efficent XAI Information Saliency Tool

RESOURCE

Abstract

This software is an implementation which is described in: "Efficient Saliency Maps for Explainable AI" (https://openreview.net/forum?id=ryxf9CEKDr). The toolkit is located in: https://mybitbucket.llnl.gov/projects/SAL/repos/smoe_lovi/browse. It is a set of of PyTorch related python scripts for extracting the what parts of an image are most salient to a deep neural network in an efficient manner. This source will allow one to replicate the results in the paper referenced above. Is there
Developers:
MUNDHENK, TERRELL [1] CHEN, BARRY [1] FRIEDLAND, GERALD [1]
  1. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Release Date:
2019-10-22
Project Type:
Open Source, Publicly Available Repository
Software Type:
Scientific
Version:
1.0
Licenses:
BSD 3-clause "New" or "Revised" License
Sponsoring Org.:
Code ID:
35964
Site Accession Number:
LLNL-CODE-802426
Research Org.:
Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Country of Origin:
United States

RESOURCE

Citation Formats

MUNDHENK, TERRELL N., CHEN, BARRY Y., and FRIEDLAND, GERALD. Efficent XAI Information Saliency Tool. Computer Software. https://github.com/LLNL/fastcam. USDOE National Nuclear Security Administration (NNSA). 22 Oct. 2019. Web. doi:10.11578/dc.20200513.2.
MUNDHENK, TERRELL N., CHEN, BARRY Y., & FRIEDLAND, GERALD. (2019, October 22). Efficent XAI Information Saliency Tool. [Computer software]. https://github.com/LLNL/fastcam. https://doi.org/10.11578/dc.20200513.2.
MUNDHENK, TERRELL N., CHEN, BARRY Y., and FRIEDLAND, GERALD. "Efficent XAI Information Saliency Tool." Computer software. October 22, 2019. https://github.com/LLNL/fastcam. https://doi.org/10.11578/dc.20200513.2.
@misc{ doecode_35964,
title = {Efficent XAI Information Saliency Tool},
author = {MUNDHENK, TERRELL N. and CHEN, BARRY Y. and FRIEDLAND, GERALD},
abstractNote = {This software is an implementation which is described in: "Efficient Saliency Maps for Explainable AI" (https://openreview.net/forum?id=ryxf9CEKDr). The toolkit is located in: https://mybitbucket.llnl.gov/projects/SAL/repos/smoe_lovi/browse. It is a set of of PyTorch related python scripts for extracting the what parts of an image are most salient to a deep neural network in an efficient manner. This source will allow one to replicate the results in the paper referenced above. Is there},
doi = {10.11578/dc.20200513.2},
url = {https://doi.org/10.11578/dc.20200513.2},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20200513.2}},
year = {2019},
month = {oct}
}