Self-Supervised Structure Learning for Crack Detection Based on Cycle-Consistent Generative Adversarial Networks

Zhang, Kaige; Zhang, Yingtao; Cheng, Heng-Da

doi:10.1061/(asce)cp.1943-5487.0000883

Cited by 59 publications

(28 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast, as a new paradigm between unsupervised and supervised learning, SSL can generate labels based on the property of unlabeled data itself to train the neural network in a supervised manner similar to natural learning experiences. With excellent performance on representation learning and dealing with the issue of unlabelled data, SSL [20][21][22] has been successfully implemented in a wide range of fields, including image recognition 23 , audio representation 24 , computer vision 25 , document reconstruction 26 , atmosphere 27 , astronomy 28 , medical 29 , person re-identification 30 , remote sensing 31 , robotics 32 , omnidirectional imaging 33 , manufacturing 34 , nano-photonics 35 , and civil engineering 36 , etc. However, this method has not been formally attempted in material science.…”

Section: High-efficient Low-cost Characterization Of Materials Properties Using Domain-knowledge-guided Selfsupervised Learningmentioning

confidence: 99%

High-efficient low-cost characterization of materials properties using domain-knowledge-guided self-supervised learning

Xie

Yao

Mao

et al. 2022

Preprint

View full text Add to dashboard Cite

Modern AI-assisted approaches have helped material scientists revolutionize their abilities to better understand the properties of materials. However, current machine learning (ML) models would perform awful for materials with a lengthy production window and a complex testing procedure because only a limited amount of data can be produced to feed the model. Here, we introduce self-supervised learning (SSL) to address the issue of lacking labeled data in material characterization. We propose a generalized SSL-based framework with domain knowledge and demonstrate its robustness to predict the properties of a candidate material with the fewest data. Our numerical results show that the performance of the proposed SSL model can match the commonly-used supervised learning (SL) model with only 5 % of data, and the SSL model is also proven with ease of implementation. Our study paves the way to expand further the usability of ML tools for a broader material science community.

show abstract

Section: High-efficient Low-cost Characterization Of Materials Properties Using Domain-knowledge-guided Selfsupervised Learningmentioning

confidence: 99%

High-efficient low-cost characterization of materials properties using domain-knowledge-guided self-supervised learning

Xie

Yao

Mao

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In addition to the aforementioned metrics, three other parameters, including precision (P) (Equation ( 14)), recall (R) (Equation ( 15)), and F-score (F) (Equation ( 16)), were also used for the performance evaluation of the proposed crack detection CNN model. These metrics, including P, R, and F, were calculated to evaluate the semantic segmentation using equations 18-20 [66,67]. P represents the predictions for a positive class included in the collected dataset.…”

Section: Evaluation Metricsmentioning

confidence: 99%

“…These parameters were used in the current study to evaluate image segmentation. Additionally, the IoU parameter was used to quantify common pixels between the target mask and predictions of the outputs [29,67]. It is notable that for the selected crack dataset, the IoU_min values increased from 0.1 to 0.9 while calculating the error on each point.…”

Section: Training and Test Accuracymentioning

confidence: 99%

See 1 more Smart Citation

Inspecting Buildings Using Drones and Computer Vision: A Machine Learning Approach to Detect Cracks and Damages

Munawar

Ullah

Heravi

et al. 2021

Drones

View full text Add to dashboard Cite

Manual inspection of infrastructure damages such as building cracks is difficult due to the objectivity and reliability of assessment and high demands of time and costs. This can be automated using unmanned aerial vehicles (UAVs) for aerial imagery of damages. Numerous computer vision-based approaches have been applied to address the limitations of crack detection but they have their limitations that can be overcome by using various hybrid approaches based on artificial intelligence (AI) and machine learning (ML) techniques. The convolutional neural networks (CNNs), an application of the deep learning (DL) method, display remarkable potential for automatically detecting image features such as damages and are less sensitive to image noise. A modified deep hierarchical CNN architecture has been used in this study for crack detection and damage assessment in civil infrastructures. The proposed architecture is based on 16 convolution layers and a cycle generative adversarial network (CycleGAN). For this study, the crack images were collected using UAVs and open-source images of mid to high rise buildings (five stories and above) constructed during 2000 in Sydney, Australia. Conventionally, a CNN network only utilizes the last layer of convolution. However, our proposed network is based on the utility of multiple layers. Another important component of the proposed CNN architecture is the application of guided filtering (GF) and conditional random fields (CRFs) to refine the predicted outputs to get reliable results. Benchmarking data (600 images) of Sydney-based buildings damages was used to test the proposed architecture. The proposed deep hierarchical CNN architecture produced superior performance when evaluated using five methods: GF method, Baseline (BN) method, Deep-Crack BN, Deep-Crack GF, and SegNet. Overall, the GF method outperformed all other methods as indicated by the global accuracy (0.990), class average accuracy (0.939), mean intersection of the union overall classes (IoU) (0.879), precision (0.838), recall (0.879), and F-score (0.8581) values. Overall, the proposed CNN architecture provides the advantages of reduced noise, highly integrated supervision of features, adequate learning, and aggregation of both multi-scale and multilevel features during the training procedure along with the refinement of the overall output predictions.

show abstract

“…Zou et al [28] presented a pseudo-labeling technique to generate structured pseudo-labels with unlabeled or weakly labeled data. In [29], a self-supervised structure learning network that can be trained without using a GT was introduced. This is achieved by training a reverse network to return the output to the input.…”

Section: Introductionmentioning

confidence: 99%

Automated Ground Truth Generation for Learning-Based Crack Detection on Concrete Surfaces

Chen

2021

Applied Sciences

View full text Add to dashboard Cite

This article introduces an automated data-labeling approach for generating crack ground truths (GTs) within concrete images. The main algorithm includes generating first-round GTs, pre-training a deep learning-based model, and generating second-round GTs. On the basis of the generated second-round GTs of the training data, a learning-based crack detection model can be trained in a self-supervised manner. The pre-trained deep learning-based model is effective for crack detection after it is re-trained using the second-round GTs. The main contribution of this study is the proposal of an automated GT generation process for training a crack detection model at the pixel level. Experimental results show that the second-round GTs are similar to manually marked labels. Accordingly, the cost of implementing learning-based methods is reduced significantly because data labeling by humans is not necessitated.

show abstract

Self-Supervised Structure Learning for Crack Detection Based on Cycle-Consistent Generative Adversarial Networks

Cited by 59 publications

References 55 publications

High-efficient low-cost characterization of materials properties using domain-knowledge-guided self-supervised learning

High-efficient low-cost characterization of materials properties using domain-knowledge-guided self-supervised learning

Inspecting Buildings Using Drones and Computer Vision: A Machine Learning Approach to Detect Cracks and Damages

Automated Ground Truth Generation for Learning-Based Crack Detection on Concrete Surfaces

Contact Info

Product

Resources

About