Name:
PRIME
Description:
Boost robustness of images to common corruptions
Professor — Lab:
Pascal FrossardSignal Processing Laboratory

Technical description:
PRIME is a generic, plug-n-play data augmentation scheme that consists of simple families of max-entropy image transformations for conferring robustness to common corruptions. PRIME leads to significant improvements in corruption robustness on multiple benchmarks.
Papers:
Project status:
inactive — entered showcase: 2022-07-06 — entry updated: 2024-03-21

Source code:
Lab GitHub - last commit: 2021-12-28
Code quality:
This project has not yet been evaluated by the C4DT Factory team. We will be happy to evaluate it upon request.
Project type:
Toolset
Programming language:
Python
License:
Apache-2.0