Dual-Space Augmented Intrinsic-LoRA for Wind Turbine Segmentation

TL;DR

This paper introduces a dual-space augmentation strategy combined with Intrinsic LoRA to improve wind turbine blade segmentation accuracy, outperforming existing methods in domain-specific image segmentation tasks.

Contribution

It extends Intrinsic LoRA with a novel dual-space augmentation approach that integrates image-level and latent-space augmentations for enhanced segmentation performance.

Findings

Achieves higher segmentation accuracy than state-of-the-art methods.

Demonstrates effectiveness of dual-space augmentation in domain-specific segmentation.

Significantly improves wind turbine blade image segmentation results.

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.