Recent studies indicate that deep learning plays a crucial role in the automated visual inspection of road infrastructures. However, current learning schemes are static, implying no dynamic adaptation to users' feedback. To address this drawback, we present a few-shot learning paradigm for the automated segmentation of road cracks, which is based on a U-Net architecture with recurrent residual and attention modules (R2AU-Net). The retraining strategy dynamically fine-tunes the weights of the U-Net as a few new rectified samples are being fed into the classifier. Extensive experiments show that the proposed few-shot R2AU-Net framework outperforms other state-of-the-art networks in terms of Dice and IoU metrics, on a new dataset, named CrackMap, which is made publicly available at https://github.com/ikatsamenis/CrackMap.
@article{arxiv.2303.01582,
title = {A Few-Shot Attention Recurrent Residual U-Net for Crack Segmentation},
author = {Iason Katsamenis and Eftychios Protopapadakis and Nikolaos Bakalos and Anastasios Doulamis and Nikolaos Doulamis and Athanasios Voulodimos},
journal= {arXiv preprint arXiv:2303.01582},
year = {2023}
}