Publication

Dual-space augmented intrinsic-LoRA for wind turbine segmentation

Conference Article

Conference

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Edition

2025

Pages

1-5

Doc link

http://dx.doi.org/10.1109/ICASSP49660.2025.10890002

File

Download the digital copy of the doc pdf document

Abstract

Accurate segmentation of wind turbine blade (WTB) images is critical for effective assessments, as it directly influences the performance of automated damage detection systems. Despite advancements in large universal vision models, these models often underperform in domain-specific tasks like WTB segmentation. To address this, we extend Intrinsic LoRA for image segmentation, and propose a novel dual-space augmentation strategy that integrates both image-level and latent-space augmentations. The image-space augmentation is achieved through linear interpolation between image pairs, while the latent-space augmentation is accomplished by introducing a noise-based latent probabilistic model. Our approach significantly boosts segmentation accuracy, surpassing current state-of-the-art methods in WTB image segmentation.

Categories

edge detection, feature extraction.

Author keywords

Latent-space Augmentation, Diffusion Models, LoRA, Image Segmentation, Wind Turbine Blade

Scientific reference

S. Singhal, R. Pérez, A. Espersen and A. Agudo. Dual-space augmented intrinsic-LoRA for wind turbine segmentation, 2025 IEEE International Conference on Acoustics, Speech and Signal Processing, 2025, Hyderabad, India, pp. 1-5.