A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Efficient semi-supervised surface crack segmentation with small datasets based on consistency regularisation and pseudo-labelling
Abstract Despite promising results in vision-based surface crack detection, data-driven approaches still suffer from the scarcity of rich labelled datasets. Such a limitation has hindered a wider practical application of detection models. To address this issue, a semi-supervised framework is proposed, capable of learning from a substantial amount of unlabelled data and achieving high accuracy, even when the available labelled datasets are of limited size. The framework is designed by tailoring supervised training, semi-supervised consistency regularisation, and self-training with certainty-based pseudo-labelling, resulting in a simple yet effective approach. Despite using only 2% of the total labelled Concrete and Asphalt datasets, the resulting mIoU was only 2.6% and 4.7%, respectively, lower than the best performance of the model trained on 100% of the labelled data. Remarkably, the designed framework assisted the model in approaching and even exceeding saturation levels with as little as 20% and 25% of the Concrete and Asphalt datasets.
Highlights A semi-supervised framework is proposed for surface crack semantic segmentation. The framework leverages consistency regularisation and pseudo-labelling. Precise crack segmentation is achieved with small datasets. The framework achieved promising results, with 2 and 98% of images as labelled and unlabelled data. Saturation of the accuracy scores is achieved with <25% of the labelled data.
Efficient semi-supervised surface crack segmentation with small datasets based on consistency regularisation and pseudo-labelling
Abstract Despite promising results in vision-based surface crack detection, data-driven approaches still suffer from the scarcity of rich labelled datasets. Such a limitation has hindered a wider practical application of detection models. To address this issue, a semi-supervised framework is proposed, capable of learning from a substantial amount of unlabelled data and achieving high accuracy, even when the available labelled datasets are of limited size. The framework is designed by tailoring supervised training, semi-supervised consistency regularisation, and self-training with certainty-based pseudo-labelling, resulting in a simple yet effective approach. Despite using only 2% of the total labelled Concrete and Asphalt datasets, the resulting mIoU was only 2.6% and 4.7%, respectively, lower than the best performance of the model trained on 100% of the labelled data. Remarkably, the designed framework assisted the model in approaching and even exceeding saturation levels with as little as 20% and 25% of the Concrete and Asphalt datasets.
Highlights A semi-supervised framework is proposed for surface crack semantic segmentation. The framework leverages consistency regularisation and pseudo-labelling. Precise crack segmentation is achieved with small datasets. The framework achieved promising results, with 2 and 98% of images as labelled and unlabelled data. Saturation of the accuracy scores is achieved with <25% of the labelled data.
Efficient semi-supervised surface crack segmentation with small datasets based on consistency regularisation and pseudo-labelling
Asadi Shamsabadi, Elyas (author) / Erfani, Seyed Mohammad Hassan (author) / Xu, Chang (author) / Dias-da-Costa, Daniel (author)
2023-11-02
Article (Journal)
Electronic Resource
English
Semi-supervised semantic segmentation using cross-consistency training for pavement crack detection
| Taylor & Francis Verlag | 2024
Crack Modelling and Regularisation
| Wiley | 2022
Regularisation behaviour of the viscoplastic consistency model
| British Library Conference Proceedings | 2003