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

arXiv: https://arxiv.org/abs/2102.03858 · HTML: https://mlsanity.com/paper/2102.03858/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 89 references that are in the map.
- First posted on arXiv 7 Feb 2021.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)
- [Rethinking ImageNet Pre-training](https://mlsanity.com/paper/1811.08883/) (2018)
- [Transfusion: Understanding Transfer Learning for Medical Imaging](https://mlsanity.com/paper/1902.07208/) (2019)
- [What makes ImageNet good for transfer learning?](https://mlsanity.com/paper/1608.08614/) (2016)
- [The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation](https://mlsanity.com/paper/1611.09326/) (2016)
- [On Interpretability of Artificial Neural Networks: A Survey](https://mlsanity.com/paper/2001.02522/) (2020)
- [Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era](https://mlsanity.com/paper/1906.06543/) (2019)
- [Potential, Challenges and Future Directions for Deep Learning in Prognostics and Health Management Applications](https://mlsanity.com/paper/2005.02144/) (2020)
- [CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization](https://mlsanity.com/paper/2004.15004/) (2020)
- [Road Damage Detection Using Deep Neural Networks with Images Captured Through a Smartphone](https://mlsanity.com/paper/1801.09454/) (2018)
- [In-domain representation learning for remote sensing](https://mlsanity.com/paper/1911.06721/) (2019)
- [Investigating Transferability in Pretrained Language Models](https://mlsanity.com/paper/2004.14975/) (2020)
- [Meta-learning Convolutional Neural Architectures for Multi-target Concrete Defect Classification with the COncrete DEfect BRidge IMage Dataset](https://mlsanity.com/paper/1904.08486/) (2019)
- [Road surface detection and differentiation considering surface damages](https://mlsanity.com/paper/2006.13377/) (2020)
- [Bridge Damage Detection using a Single-Stage Detector and Field Inspection Images](https://mlsanity.com/paper/1812.10590/) (2018)
- [Cross-domain attribute representation based on convolutional neural network](https://mlsanity.com/paper/1805.07295/) (2018)
- [Automated Pavement Crack Segmentation Using U-Net-based Convolutional Neural Network](https://mlsanity.com/paper/2001.01912/) (2020)
- [Learning convolutional neural network to maximize Pos@Top performance measure](https://mlsanity.com/paper/1609.08417/) (2016)

## Built on by (most cited first, 7 of 7)

- [Building Inspection Toolkit: Unified Evaluation and Strong Baselines for Damage Recognition](https://mlsanity.com/paper/2202.07012/) (2022)
- [A Novel Strategy for Improving Robustness in Computer Vision Manufacturing Defect Detection](https://mlsanity.com/paper/2305.09407/) (2023)
- [dacl1k: Real-World Bridge Damage Dataset Putting Open-Source Data to the Test](https://mlsanity.com/paper/2309.03763/) (2023)
- [Analysis of the Two-Step Heterogeneous Transfer Learning for Laryngeal Blood Vessel Classification: Issue and Improvement](https://mlsanity.com/paper/2402.19001/) (2024)
- [Deep Learning for Segmentation of Cracks in High-Resolution Images of Steel Bridges](https://mlsanity.com/paper/2403.17725/) (2024)
- [Instance Segmentation of Reinforced Concrete Bridges with Synthetic Point Clouds](https://mlsanity.com/paper/2409.16381/) (2024)
- [Deep Learning with Self-Attention and Enhanced Preprocessing for Precise Diagnosis of Acute Lymphoblastic Leukemia from Bone Marrow Smears in Hemato-Oncology](https://mlsanity.com/paper/2508.17216/) (2025)

## Abstract (arXiv)

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.