Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

DECIDER

Software ·
DOI:https://doi.org/10.11578/dc.20250529.2· OSTI ID:code-156111 · Code ID:156111
 [1];  [1];  [1]
  1. Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)

This software offers methods and functions for building failure detectors for deep image classification models with the aid of vision-language models and LLMs. It includes functionalities for training baseline image classifiers, debiasing classifiers using vision-language models and LLMs, evaluating failure between models along with baselines. Developed using PyTorch, this software is compatible with standard neural network architectures used for imaging data. Additionally, it provides capabilities to compute evaluation metrics for assessing the performance and quality of the detectors.

Short Name / Acronym:
DECIDER
Site Accession Number:
LLNL-CODE-2000765
Software Type:
Scientific
License(s):
MIT 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:
156111
OSTI ID:
code-156111
Country of Origin:
United States

Similar Records

Know Your Space: Inlier and Outlier Construction for Calibrating Medical OOD Detectors
Software · Sun Jun 04 20:00:00 EDT 2023 · OSTI ID:code-108775

Anchoring
Software · Tue Oct 29 20:00:00 EDT 2024 · OSTI ID:code-153374

Graphene U-Net v1
Software · Mon Jun 07 20:00:00 EDT 2021 · OSTI ID:code-60277

Related Subjects