Abstract
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.
- Developers:
-
Narayanaswamy, Vivek Sivaraman [1] ; Thopalli, Kowshik [1] ; Subramanyam, Rakshith [1]
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
- Release Date:
- 2024-09-20
- Project Type:
- Open Source, Publicly Available Repository
- Software Type:
- Scientific
- Version:
- 0.1
- Licenses:
-
MIT License
- Sponsoring Org.:
-
USDOE National Nuclear Security Administration (NNSA)Primary Award/Contract Number:AC52-07NA27344
- Code ID:
- 156111
- Site Accession Number:
- LLNL-CODE-2000765
- Research Org.:
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
- Country of Origin:
- United States
Citation Formats
Narayanaswamy, Vivek Sivaraman, Thopalli, Kowshik, and Subramanyam, Rakshith.
DECIDER.
Computer Software.
https://github.com/LLNL/DECIDER.
USDOE National Nuclear Security Administration (NNSA).
20 Sep. 2024.
Web.
doi:10.11578/dc.20250529.2.
Narayanaswamy, Vivek Sivaraman, Thopalli, Kowshik, & Subramanyam, Rakshith.
(2024, September 20).
DECIDER.
[Computer software].
https://github.com/LLNL/DECIDER.
https://doi.org/10.11578/dc.20250529.2.
Narayanaswamy, Vivek Sivaraman, Thopalli, Kowshik, and Subramanyam, Rakshith.
"DECIDER." Computer software.
September 20, 2024.
https://github.com/LLNL/DECIDER.
https://doi.org/10.11578/dc.20250529.2.
@misc{
doecode_156111,
title = {DECIDER},
author = {Narayanaswamy, Vivek Sivaraman and Thopalli, Kowshik and Subramanyam, Rakshith},
abstractNote = {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.},
doi = {10.11578/dc.20250529.2},
url = {https://doi.org/10.11578/dc.20250529.2},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20250529.2}},
year = {2024},
month = {sep}
}