Jiahong Wei’s research while affiliated with Shantou University and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (6)


Genetic U-Net: Automatically Designed Deep Networks for Retinal Vessel Segmentation Using a Genetic Algorithm
  • Article
  • Full-text available

September 2021

·

567 Reads

·

82 Citations

IEEE Transactions on Medical Imaging

Jiahong Wei

·

·

·

[...]

·

Recently, many methods based on hand-designed convolutional neural networks (CNNs) have achieved promising results in automatic retinal vessel segmentation. However, these CNNs remain constrained in capturing retinal vessels in complex fundus images. To improve their segmentation performance, these CNNs tend to have many parameters, which may lead to overfitting and high computational complexity. Moreover, the manual design of competitive CNNs is time-consuming and requires extensive empirical knowledge. Herein, a novel automated design method, called Genetic U-Net, is proposed to generate a U-shaped CNN that can achieve better retinal vessel segmentation but with fewer architecture-based parameters, thereby addressing the above issues. First, we devised a condensed but flexible search space based on a U-shaped encoder-decoder. Then, we used an improved genetic algorithm to identify better-performing architectures in the search space and investigated the possibility of finding a superior network architecture with fewer parameters. The experimental results show that the architecture obtained using the proposed method offered a superior performance with less than 1% of the number of the original U-Net parameters in particular and with significantly fewer parameters than other state-of-the-art models. Furthermore, through in-depth investigation of the experimental results, several effective operations and patterns of networks to generate superior retinal vessel segmentations were identified. The codes of this work are available at https://github.com/96jhwei/Genetic-U-Net .

Download


Genetic U-Net: Automatically Designing Lightweight U-shaped CNN Architectures Using the Genetic Algorithm for Retinal Vessel Segmentation

October 2020

·

161 Reads

Many previous works based on deep learning for retinal vessel segmentation have achieved promising performance by manually designing U-shaped convolutional neural networks (CNNs). However, the manual design of these CNNs is time-consuming and requires extensive empirical knowledge. To address this problem, we propose a novel method using genetic algorithms (GAs) to automatically design a lightweight U-shaped CNN for retinal vessel segmentation, called Genetic U-Net. Here we first design a special search space containing the structure of U-Net and its corresponding operations, and then use genetic algorithm to search for superior architectures in this search space. Experimental results show that the proposed method outperforms the existing methods on three public datasets, DRIVE, CHASE_DB1 and STARE. In addition, the architectures obtained by the proposed method are more lightweight but robust than the state-of-the-art models.


Figure 8. Results of comparison of proposed U-HDN with other method based on public database (From left to right: input image, ground truth, Canny, local threshold, FFA, MPS, structured prediction, ensemble network, and proposed U-HDN).
Types of cracks in road pavements.
Experimental results for different dilation rates on CFD database.
Experimental results for different dilation rates on AigleRN database.
Crack detection results on CFD.

+3

Automatic Crack Detection on Road Pavements Using Encoder-Decoder Architecture

July 2020

·

742 Reads

·

127 Citations

Materials

Automatic crack detection from images is an important task that is adopted to ensure road safety and durability for Portland cement concrete (PCC) and asphalt concrete (AC) pavement. Pavement failure depends on a number of causes including water intrusion, stress from heavy loads, and all the climate effects. Generally, cracks are the first distress that arises on road surfaces and proper monitoring and maintenance to prevent cracks from spreading or forming is important. Conventional algorithms to identify cracks on road pavements are extremely time-consuming and high cost. Many cracks show complicated topological structures, oil stains, poor continuity, and low contrast, which are difficult for defining crack features. Therefore, the automated crack detection algorithm is a key tool to improve the results. Inspired by the development of deep learning in computer vision and object detection, the proposed algorithm considers an encoder-decoder architecture with hierarchical feature learning and dilated convolution, named U-Hierarchical Dilated Network (U-HDN), to perform crack detection in an end-to-end method. Crack characteristics with multiple context information are automatically able to learn and perform end-to-end crack detection. Then, a multi-dilation module embedded in an encoder-decoder architecture is proposed. The crack features of multiple context sizes can be integrated into the multi-dilation module by dilation convolution with different dilatation rates, which can obtain much more cracks information. Finally, the hierarchical feature learning module is designed to obtain a multi-scale features from the high to low- level convolutional layers, which are integrated to predict pixel-wise crack detection. Some experiments on public crack databases using 118 images were performed and the results were compared with those obtained with other methods on the same images. The results show that the proposed U-HDN method achieves high performance because it can extract and fuse different context sizes and different levels of feature maps than other algorithms.


Automatic Crack Detection on Road Pavements Using Encoder Decoder Architecture

July 2020

·

520 Reads

Inspired by the development of deep learning in computer vision and object detection, the proposed algorithm considers an encoder-decoder architecture with hierarchical feature learning and dilated convolution, named U-Hierarchical Dilated Network (U-HDN), to perform crack detection in an end-to-end method. Crack characteristics with multiple context information are automatically able to learn and perform end-to-end crack detection. Then, a multi-dilation module embedded in an encoder-decoder architecture is proposed. The crack features of multiple context sizes can be integrated into the multi-dilation module by dilation convolution with different dilatation rates, which can obtain much more cracks information. Finally, the hierarchical feature learning module is designed to obtain a multi-scale features from the high to low-level convolutional layers, which are integrated to predict pixel-wise crack detection. Some experiments on public crack databases using 118 images were performed and the results were compared with those obtained with other methods on the same images. The results show that the proposed U-HDN method achieves high performance because it can extract and fuse different context sizes and different levels of feature maps than other algorithms.


ENAS U-Net: Evolutionary Neural Architecture Search for Retinal Vessel Segmentation

January 2020

·

182 Reads

·

1 Citation

The accurate retina vessel segmentation (RVS) is of great significance to assist doctors in the diagnosis of ophthalmology diseases and other systemic diseases, and manually designing a valid neural network architecture for retinal vessel segmentation requires high expertise and a large workload. In order to further improve the performance of vessel segmentation and reduce the workload of manually designing neural network. We propose a specific search space based on encoder-decoder framework and apply neural architecture search (NAS) to retinal vessel segmentation. The search space is a macro-architecture search that involves some operations and adjustments to the entire network topology. For the architecture optimization, we adopt the modified evolutionary strategy which can evolve with limited computing resource to evolve the architectures. During the evolution, we select the elite architectures for the next generation evolution based on their performances. After the evolution, the searched model is evaluated on three mainstream datasets, namely DRIVE, STARE and CHASE_DB1. The searched model achieves top performance on all three datasets with fewer parameters (about 2.3M). Moreover, the results of cross-training between above three datasets show that the searched model is with considerable scalability, which indicates that the searched model is with potential for clinical disease diagnosis.

Citations (3)


... Several methods have been developed by researchers using disparate sensors for the automated detection of pipeline leaks [19]. [6], for example, created a caterpillar-type inspection robot with a camera for oil and gas systems that can move or crawl inside pipelines. ...

Reference:

Designing A Frugal Inspection Robot for Detecting In-Pipe Leaks in The Oil And Gas Sector
Pipeline Leak Detection, Location and Repair
  • Citing Conference Paper
  • July 2021

... Auto-reID [34] differs from expert-designed neural networks [1,10,11] as it focuses on automating the search for neural network architectures. Neural network architectures developed by NAS-based approaches have surpassed expert-designed architectures not only in image classification [35,36] but also in object detection [37,38] and segmentation [39,40]. NAS based approaches can be categorized into different groups based on the search strategy used: gradient-based [41][42][43], evolutionary algorithms based [39,40,44], and reinforcement learning based [45][46][47] approaches. ...

Genetic U-Net: Automatically Designed Deep Networks for Retinal Vessel Segmentation Using a Genetic Algorithm

IEEE Transactions on Medical Imaging

... Recently, ED-CNNs have been developed for semantic image segmentation [18]. Motivated by these accomplishments, numerous recent investigations have devised ED-CNN-based models aimed at automatic semantic segmentation of concrete cracks [19,20]. ...

Automatic Crack Detection on Road Pavements Using Encoder-Decoder Architecture

Materials