Phase-wise Parameter Aggregation For Improving SGD Optimization

Handcrafted vs. non-handcrafted features for computer vision classification

The deep learning method is widely used in computer vision tasks with large-scale annotated datasets. However, obtaining such datasets in most directions of the vision based nondestructive testing (NDT) field is very challenging. Data augmentation is proved as an efficient way of dealing with the lack of large-scale annotated datasets. In this paper, we propose a CycleGAN-based extra-supervised (CycleGAN-ES) model to generate synthetic NDT images, where the ES is used to ensure that the bidirectional mapping is learned for corresponding labels and defects. Furthermore, we show the effectiveness of using the synthesized images to train deep convolutional neural networks (DCNNs) for defect recognition. In the experiments, we extract a number of x-ray welding images with both defect and no defects from the published GDXray dataset, and CycleGAN-ES is used to generate the synthetic defect images based on a small number of extracted defect images and manually drawn labels that are used as a content guide. For quality verification of the synthesized defect images, we use a high-performance classifier pretrained using a big dataset to recognize the synthetic defects and show the comparability of the performances of classifiers trained using synthetic defects and real defects, respectively. To present the effectiveness of using the synthesized defects as an augmentation method, we train and evaluate the performances of DCNN for defect recognition with or without the synthesized defects.

With the explosive growth in seismic data acquisition and the successful application of deep convolutional neural networks (DCNN) to various image processing tasks within multidisciplinary fields, many researchers have begun to research DCNN based automatic seismic interpretation techniques. Due to the vast number of parameters considered in deep neural networks, deep learning methods usually require a large amount of data for training. However, collecting a large number of expert interpretations is very time consuming, so related research usually uses synthetic datasets and ignores the practical problems of field datasets. In this paper, we open-source a multi-gigabyte expert-labelled field dataset in response to the challenge of accessing large-scale expert-labelled field datasets. We show that 2D fault recognition within this dataset is an image segmentation or edge detection problem in the computer vision field, that can be expressed as a pixel-level fault/non-fault binary classification. Both types of DCNNs are compared, and we propose a novel fault recognition workflow, which involves processing and screening of seismic images and labels, training DCNNs and automatic numerical evaluation. We have also demonstrated for three case study datasets that effective image augmentation methods can reduce the required labelled crosslines while maintaining satisfactory performance. Our experimental results show that our workflow not only outperforms two state-of-the-art DCNN solutions but also achieves performance comparable to humans on an expert labelled image dataset, even predicting subtle faults that an expert interpreter did not annotate. We suggest that the proposed workflow could reduce the fault interpretation life cycle from months to hours and improve the quality, and define the confidence, of fault interpretation results.

We present a flexible deep convolutional neural network method for the analysis of arbitrary sized graph structures representing molecules. This method, which makes use of the Lipinski RDKit module, an open-source cheminformatics software, enables the incorporation of any global molecular (such as molecular charge and molecular weight) and local (such as atom hybridization and bond orders) information. In this paper, we show that this method significantly outperforms another recently proposed method based on deep convolutional neural networks on several datasets that are studied. Several best practices for training deep convolutional neural networks on chemical datasets are also highlighted within the article, such as how to select the information to be included in the model, how to prevent overfitting and how unbalanced classes in the data can be handled.

Deep convolutional neural network training enrichment using multi-view object-based analysis of Unmanned Aerial systems imagery for wetlands classification

PurposeDeep convolutional neural networks are favored methods that are widely used in medical image processing due to their demonstrated performance in this area. Recently, the emergence of new lung diseases, such as COVID-19, and the possibility of early detection of their symptoms from chest computerized tomography images has attracted many researchers to classify diseases by training deep convolutional neural networks on lung computerized tomography images. The trained networks are expected to distinguish between different lung indications in various diseases, especially at the early stages. The purpose of this study is to introduce and assess an efficient deep convolutional neural network, called AFEX-Net, that can classify different lung diseases from chest computerized tomography images.MethodsWe designed a lightweight convolutional neural network called AFEX-Net with adaptive feature extraction layers, adaptive pooling layers, and adaptive activation functions. We trained and tested AFEX-Net on a dataset of more than 10,000 chest computerized tomography slices from different lung diseases (CC dataset), using an effective pre-processing method to remove bias. We also applied AFEX-Net to the public COVID-CTset dataset to assess its generalizability. The study was mainly conducted based on data collected over approximately six months during the pandemic outbreak in Afzalipour Hospital, Iran, which is the largest hospital in Southeast Iran.ResultsAFEX-Net achieved high accuracy and fast training on both datasets, outperforming several state-of-the-art convolutional neural networks. It has an accuracy of and on the CC and COVID-CTset datasets, respectively, with a learning speed that is 3 times faster compared to similar methods due to its lightweight structure. AFEX-Net was able to extract distinguishing features and classify chest computerized tomography images, especially at the early stages of lung diseases.ConclusionThe AFEX-Net is a high-performing convolutional neural network for classifying lung diseases from chest CT images. It is efficient, adaptable, and compatible with input data, making it a reliable tool for early detection and diagnosis of lung diseases.

Breast cancer is a fatal disease that affects millions of women worldwide. The number of cases of breast cancer has risen over time. Although it is difficult to prevent this disease, the survival rate can be improved with early detection and proper treatment planning of the disease. Thanks to breakthroughs in deep learning, the progress of computer-assisted diagnosis (CAD) of breast cancer has seen a lot of improvement. Deep neural networks have advanced to the point where their diagnostic capabilities are approaching those of a human specialist. Mammograms are crucial radiological images used to detect breast cancer at its early stage. Mammogram image scaling at the input layer is required for training deep convolutional neural networks (DCNNs) directly on high-resolution images. This could result in the loss of crucial information for discovering medical abnormalities. Instead of developing an image classifier, the idea is to create a patch classifier. The technique for extracting abnormal patches from mammography images is proposed in this research. Patches are extracted from a benchmark and publicly available MIAS dataset. These patches are then used to train deep learning classifiers such as VGG-16, ResNet-50, and EfficientNet-B7. With the patches already included in the CBIS-DDSM dataset, we contrast the results of the MIAS patches. EfficientNet-B7 on CBIS-DDSM patches produced good results (92% accuracy) when compared to other classifiers such as VGG-16 and ResNet-50. We also discovered that ResNet-50 is demonstrated to be quite robust on both datasets.

Nowadays, satellite images are used in various governmental applications, such as urbanization and monitoring the environment. Spatial resolution is an element of crucial impact on the usage of remote sensing imagery. As such, increasing the spatial resolution of an image is an important pre-processing step that can improve the performance of various image processing tasks, such as segmentation. Once a satellite is launched, the more practical solution to improve the resolution of its captured images is to use Single Image Super Resolution (SISR) techniques. In the recent years, Deep Convolutional Neural Networks (DCNNs) have been recognized as a highly effective tool to reconstruct a High Resolution (HR) image from its Low Resolution (LR) counterpart, which is an open problem due to the inherent difficulty of estimating the missing high frequency components. The aim of this research paper is to design and implement a satellite image SISR algorithm by estimating high frequency details through training Deep Convolutional Neural Network (DCNNs) with respect to wavelet analysis. The goal is to improve the spatial resolution of multispectral remote sensing images captured by DubaiSat-2 satellite. The accuracy of the proposed algorithm is assessed using several metrics such as Peak Signal-to-Noise Ratio (PSNR), Wavelet-based Signal-to-Noise Ratio (WSNR) and Structural Similarity Index Measurement (SSIM).

Portrait style transfer using deep convolutional neural networks and facial segmentation

This paper was aimed to address the problem of image-based human age estimation. It has the following main contributions. First, we provide a comparison of three hand-crafted image features and five deep convolutional neural networks (DCNNs). Secondly, we show that the use of pre-trained DCNNs as feature extractors can transfer the knowledge of DCNNs to new datasets and domains that were not necessarily addressed in the training phase. This is achieved by only retraining a shallow regressor over the deep features. Thirdly, we provide a cross-database evaluation involving biological and apparent ages. The paper shows that transfer learning allows the use of pre-trained DCNNs regardless of the type of ages (apparent or biological) that is adopted in DCNN training. The experiments are carried out on three public databases: MORPH, PAL, and Chalearn2016.

Explainable Convolutional Neural Network for Gearbox Fault Diagnosis

Self-paced active learning for deep CNNs via effective loss function

Learning to rank has recently emerged as an attractive technique to train deep convolutional neural networks for various computer vision tasks. Pairwise ranking, in particular, has been successful in multi-label image classification, achieving state-of-the-art results on various benchmarks. However, most existing approaches use the hinge loss to train their models, which is non-smooth and thus is difficult to optimize especially with deep networks. Furthermore, they employ simple heuristics, such as top-k or thresholding, to determine which labels to include in the output from a ranked list of labels, which limits their use in the real-world setting. In this work, we propose two techniques to improve pairwise ranking based multi-label image classification: (1) we propose a novel loss function for pairwise ranking, which is smooth everywhere and thus is easier to optimize; and (2) we incorporate a label decision module into the model, estimating the optimal confidence thresholds for each visual concept. We provide theoretical analyses of our loss function in the Bayes consistency and risk minimization framework, and show its benefit over existing pairwise ranking formulations. We demonstrate the effectiveness of our approach on three large-scale datasets, VOC2007, NUS-WIDE and MS-COCO, achieving the best reported results in the literature.

The success of training deep Convolutional Neural Networks (CNNs) heavily depends on a significant amount of labelled data. Recent research has found that neural style transfer algorithms can apply the artistic style of one image to another image without changing the latter's high-level semantic content, which makes it feasible to employ neural style transfer as a data augmentation method to add more variation to the training dataset. The contribution of this paper is a thorough evaluation of the effectiveness of the neural style transfer as a data augmentation method for image classification tasks. We explore the state-of-the-art neural style transfer algorithms and apply them as a data augmentation method on Caltech 101 and Caltech 256 dataset, where we found around 2% improvement from 83% to 85% of the image classification accuracy with VGG16, compared with traditional data augmentation strategies. We also combine this new method with conventional data augmentation approaches to further improve the performance of image classification. This work shows the potential of neural style transfer in computer vision field, such as helping us to reduce the difficulty of collecting sufficient labelled data and improve the performance of generic image-based deep learning algorithms.

Cell detection is an important topic in biomedical image analysis and it is often the prerequisite for the following segmentation or classification procedures. In this paper, we propose a novel algorithm for general cell detection problem: Firstly, a set of cell detection candidates is generated using different algorithms with varying parameters. Secondly, each candidate is assigned a score by a trained deep convolutional neural network (DCNN). Finally, a subset of best detection results are selected from all candidates to compose the final cell detection results. The subset selection task is formalized as a maximum-weight independent set problem, which is designed to find the heaviest subset of mutually non-adjacent nodes in a graph. Experiments show that the proposed general cell detection algorithm provides detection results that are dramatically better than any individual cell detection algorithm.