Efficent XAI Information Saliency Tool

Software · Tue Oct 22 00:00:00 EDT 2019

DOI:https://doi.org/10.11578/dc.20200513.2· OSTI ID:1618298 · Code ID:35964

MUNDHENK, TERRELL N ^[1]; CHEN, BARRY Y ^[1]; FRIEDLAND, GERALD ^[1]

---

1. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)

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

• Short Name / Acronym: EXIST
• Project Type: Open Source, Publicly Available Repository
• Site Accession Number: LLNL-CODE-802426
• Software Type: Scientific
• Version: 1.0
• License(s): BSD 3-clause "New" or "Revised" License
• Research Organization: Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
• Sponsoring Organization: USDOE National Nuclear Security Administration (NNSA)

  ---

  Primary Award/Contract Number:

  AC52-07NA27344
• DOE Contract Number: AC52-07NA27344
• Code ID: 35964
• OSTI ID: 1618298
• Country of Origin: United States