Data Validation Experiments with a Computer-Generated Imagery Dataset for International Nuclear Safeguards
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Computer vision models have great potential as tools for international nuclear safeguards verification activities, but off-the-shelf models require fine-tuning through transfer learning to detect relevant objects. Because open-source examples of safeguards-relevant objects are rare, and to evaluate the potential of synthetic training data for computer vision, we present the Limbo dataset. Limbo includes both real and computer-generated images of uranium hexafluoride containers for training computer vision models. Here, we generated these images iteratively based on results from data validation experiments that are detailed here. The findings from these experiments are applicable both for the safeguards community and the broader community of computer vision research using synthetic data.
- Research Organization:
- Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA), Office of Defense Nuclear Nonproliferation
- Grant/Contract Number:
- NA0003525
- OSTI ID:
- 2311269
- Report Number(s):
- SAND--2024-00305J
- Journal Information:
- ESARDA Bulletin, Journal Name: ESARDA Bulletin Vol. 65; ISSN 0392-3029
- Publisher:
- European Safeguards Research & Development AssociationCopyright Statement
- Country of Publication:
- United States
- Language:
- English
Similar Records
Deep Deception: Exemplars of Adversarial Machine Learning and Countermeasures Applicable to International Safeguards
How Low Can You Go? Using Synthetic 3D Imagery to Drastically Reduce Real-World Training Data for Object Detection