CrackUDA: Incremental Unsupervised Domain Adaptation for Improved Crack Segmentation in Civil Structures

TL;DR

CrackUDA introduces an incremental unsupervised domain adaptation deep network with adversarial learning for crack segmentation, enhancing accuracy and generalization across diverse civil structure datasets without sacrificing source domain performance.

Contribution

The paper presents a novel encoder-decoder network with domain-invariant and domain-specific parameters for improved crack segmentation under domain shifts, along with a new dataset BuildCrack.

Findings

Significant improvement in segmentation accuracy on multiple datasets.

Enhanced generalization across different domain shifts.

Outperforms state-of-the-art UDA methods in experiments.

Abstract

Crack segmentation plays a crucial role in ensuring the structural integrity and seismic safety of civil structures. However, existing crack segmentation algorithms encounter challenges in maintaining accuracy with domain shifts across datasets. To address this issue, we propose a novel deep network that employs incremental training with unsupervised domain adaptation (UDA) using adversarial learning, without a significant drop in accuracy in the source domain. Our approach leverages an encoder-decoder architecture, consisting of both domain-invariant and domain-specific parameters. The encoder learns shared crack features across all domains, ensuring robustness to domain variations. Simultaneously, the decoder's domain-specific parameters capture domain-specific features unique to each domain. By combining these components, our model achieves improved crack segmentation performance. Furthermore, we introduce BuildCrack, a new crack dataset comparable to sub-datasets of the well-established CrackSeg9K dataset in terms of image count and crack percentage. We evaluate our proposed approach against state-of-the-art UDA methods using different sub-datasets of CrackSeg9K and our custom dataset. Our experimental results demonstrate a significant improvement in crack segmentation accuracy and generalization across target domains compared to other UDA methods - specifically, an improvement of 0.65 and 2.7 mIoU on source and target domains respectively.