An incremental unsupervised domain adaptation method with domain-specific adapter layers improves crack segmentation mIoU by 0.65 on source and 2.7 on target over the FADA baseline.
In: Proceedings of the IEEE/CVF International Conference on Computer Vision
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
CrackUDA: Incremental Unsupervised Domain Adaptation for Improved Crack Segmentation in Civil Structures
An incremental unsupervised domain adaptation method with domain-specific adapter layers improves crack segmentation mIoU by 0.65 on source and 2.7 on target over the FADA baseline.