Damage detection using in-domain and cross-domain transfer learning

TL;DR

This paper explores the effectiveness of combining in-domain and cross-domain transfer learning for damage detection in concrete structures, demonstrating improved performance especially with small datasets and enhancing model transparency.

Contribution

It introduces a comprehensive comparison of in-domain and cross-domain transfer learning strategies for damage detection, highlighting their combined benefits and providing visual explanations for model interpretability.

Findings

Combined transfer learning strategies outperform individual approaches.

Performance is notably improved with tiny datasets.

Visual explanations aid in understanding model decisions.

Abstract

We investigate the capabilities of transfer learning in the area of structural health monitoring. In particular, we are interested in damage detection for concrete structures. Typical image datasets for such problems are relatively small, calling for the transfer of learned representation from a related large-scale dataset. Past efforts of damage detection using images have mainly considered cross-domain transfer learning approaches using pre-trained IMAGENET models that are subsequently fine-tuned for the target task. However, there are rising concerns about the generalizability of IMAGENET representations for specific target domains, such as for visual inspection and medical imaging. We, therefore, evaluate a combination of in-domain and cross-domain transfer learning strategies for damage detection in bridges. We perform comprehensive comparisons to study the impact of cross-domain and in-domain transfer, with various initialization strategies, using six publicly available visual inspection datasets. The pre-trained models are also evaluated for their ability to cope with the extremely low-data regime. We show that the combination of cross-domain and in-domain transfer persistently shows superior performance specially with tiny datasets. Likewise, we also provide visual explanations of predictive models to enable algorithmic transparency and provide insights to experts about the intrinsic decision logic of typically black-box deep models.