Perceptual Similarity is a dataset about human perceptual similarity judgment. This dataset systematically evaluates deep features of different architectures and tasks, and finds that perceptual similarity is an emerging property shared by deep visual representations. The dataset includes:

• Learning Perceptual Image Patch Similarity Metric (LPIPS)
• Berkeley-Adobe Perceptual Patch Similarity Dataset (BAPPS) Sample Data

Citation

@inproceedings{zhang2018perceptual,
title={The Unreasonable Effectiveness of Deep Features as a Perceptual Metric},
author={Zhang, Richard and Isola, Phillip and Efros, Alexei A and Shechtman, Eli and Wang, Oliver},
booktitle={CVPR},
year={2018}
}