mlsanityData to 14 Oct 2026

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

arXiv 2412.15637 ↗First posted 20 Dec 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 52 references that are in the map. First posted on arXiv 20 Dec 2024.

Builds on

28 of 52 references.

References · 28

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  4. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  5. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  6. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
  7. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  8. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  9. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 472
  10. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 443
  11. 2019Confidence Regularized Self-Trainingcited by 419
  12. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 300
16 more
  1. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  2. 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 243
  3. 2020DACS: Domain Adaptation via Cross-domain Mixed Samplingcited by 226
  4. 2020Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervisioncited by 198
  5. 2018DLOW: Domain Flow for Adaptation and Generalizationcited by 177
  6. 2020Instance Adaptive Self-Training for Unsupervised Domain Adaptationcited by 177
  7. 2019Domain Adaptation for Structured Output via Discriminative Patch Representationscited by 150
  8. 2020Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentationcited by 142
  9. 2019Domain Adaptation for Semantic Segmentation with Maximum Squares Losscited by 138
  10. 2019Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentationcited by 126
  11. 2019Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detectioncited by 80
  12. 2023Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Drivingcited by 29
  13. 2021Multi-Domain Incremental Learning for Semantic Segmentationcited by 25
  14. 2022CrackSeg9k: A Collection and Benchmark for Crack Segmentation Datasets and Frameworkscited by 22
  15. 2018Unsupervised Domain Adaptation with Adversarial Residual Transform Networkscited by 14
  16. 2021Weakly-Supervised Surface Crack Segmentation by Generating Pseudo-Labels using Localization with a Classifier and Thresholdingcited by 6

Built on by

Not cited yet.