QuadFormer: Quadruple Transformer for Unsupervised Domain Adaptation in Power Line Segmentation of Aerial Images
This work addresses the labor-intensive annotation process for power line segmentation to enhance flight safety for aerial vehicles, presenting an incremental improvement in domain adaptation methods.
The paper tackles the problem of noisy pseudo labels in unsupervised domain adaptation for power line segmentation in aerial images by proposing QuadFormer, a hierarchical quadruple transformer that combines cross-attention and self-attention mechanisms with a pseudo label correction scheme, achieving state-of-the-art performance on datasets like ARPLSyn→TTTPLA and ARPLSyn→ARPLReal.
Accurate segmentation of power lines in aerial images is essential to ensure the flight safety of aerial vehicles. Acquiring high-quality ground truth annotations for training a deep learning model is a laborious process. Therefore, developing algorithms that can leverage knowledge from labelled synthetic data to unlabelled real images is highly demanded. This process is studied in Unsupervised domain adaptation (UDA). Recent approaches to self-training have achieved remarkable performance in UDA for semantic segmentation, which trains a model with pseudo labels on the target domain. However, the pseudo labels are noisy due to a discrepancy in the two data distributions. We identify that context dependency is important for bridging this domain gap. Motivated by this, we propose QuadFormer, a novel framework designed for domain adaptive semantic segmentation. The hierarchical quadruple transformer combines cross-attention and self-attention mechanisms to adapt transferable context. Based on cross-attentive and self-attentive feature representations, we introduce a pseudo label correction scheme to online denoise the pseudo labels and reduce the domain gap. Additionally, we present two datasets - ARPLSyn and ARPLReal to further advance research in unsupervised domain adaptive powerline segmentation. Finally, experimental results indicate that our method achieves state-of-the-art performance for the domain adaptive power line segmentation on ARPLSyn$\rightarrow$TTTPLA and ARPLSyn$\rightarrow$ARPLReal.