Data shift is a gap between data distribution used for training and data distribution encountered in the real-world. Data augmentations help narrow the gap by generating new data samples, increasing data variability, and data space coverage. We present a new data augmentation: Unproportional mosaicing (Unprop). Our augmentation randomly splits an image into various-sized blocks and swaps its content (pixels) while maintaining block sizes. Our method achieves a lower error rate when combined with other state-of-the-art augmentations.
@article{arxiv.2303.02081,
title = {Unproportional mosaicing},
author = {Vojtech Molek and Petr Hurtik and Pavel Vlasanek and David Adamczyk},
journal= {arXiv preprint arXiv:2303.02081},
year = {2023}
}