Balanced Semi-Supervised Generative Adversarial Network for Damage Assessment from Low-Data Imbalanced-Class Regime

TL;DR

This paper introduces BSS-GAN, a novel semi-supervised GAN variant that effectively addresses data scarcity and class imbalance in structural damage assessment, outperforming traditional methods in accuracy and recall.

Contribution

The paper proposes BSS-GAN, which combines semi-supervised learning with balanced-batch sampling to improve damage detection in low-data, imbalanced-class scenarios.

Findings

BSS-GAN outperforms conventional methods in damage detection accuracy.

It achieves higher recall and Fβ scores in concrete damage classification.

The approach is effective with limited computational resources.

Abstract

In recent years, applying deep learning (DL) to assess structural damages has gained growing popularity in vision-based structural health monitoring (SHM). However, both data deficiency and class-imbalance hinder the wide adoption of DL in practical applications of SHM. Common mitigation strategies include transfer learning, over-sampling, and under-sampling, yet these ad-hoc methods only provide limited performance boost that varies from one case to another. In this work, we introduce one variant of the Generative Adversarial Network (GAN), named the balanced semi-supervised GAN (BSS-GAN). It adopts the semi-supervised learning concept and applies balanced-batch sampling in training to resolve low-data and imbalanced-class problems. A series of computer experiments on concrete cracking and spalling classification were conducted under the low-data imbalanced-class regime with limited computing power. The results show that the BSS-GAN is able to achieve better damage detection in terms of recall and $F_\beta$ score than other conventional methods, indicating its state-of-the-art performance.