Xiaomin Yang

Xiaomin Yang
Sichuan University | SCU · College of Electronics and Information Engineering

PhD

About

168
Publications
22,680
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,898
Citations
Citations since 2016
117 Research Items
1773 Citations
20162017201820192020202120220100200300400500
20162017201820192020202120220100200300400500
20162017201820192020202120220100200300400500
20162017201820192020202120220100200300400500

Publications

Publications (168)
Article
In recent years, deep Convolutional Neural Networks (CNNs) have achieved impressive successes on the Single Image Super-Resolution task (SISR). However, it remains difficult to apply these CNN-based SISR methods in embedded devices due to their high memory and computational requirements. To alleviate this issue, we focus on lightweight SISR methods...
Preprint
Full-text available
Previous single-image super-resolution (SISR) methods assume that the blur kernel is known (e.g.,bicubic) when degrading from high-resolution (HR) images to low-resolution (LR) images. They usea single degradation to train a model to restore HR images. However, the actual degradation inreal-world is often unknown. It is difficult to deal with LR im...
Article
Full-text available
Super-resolution has attracted academic attention recently, for its capabilities of image restoration and image enhancement. To generate informative high-level features for a better reconstruction performance, most super-resolution networks have many parameters, which limit their application in resource-constrained devices. Feedback networks can ge...
Article
Full-text available
Recently, with the rapid development of deep learning (DL), an increasing number of DL-based methods are applied in pansharpening. Benefiting from the powerful feature extraction capability of deep learning, DL-based methods have achieved state-of-the-art performance in pansharpening. However, most DL-based methods simply fuse multi-spectral (MS) i...
Article
Full-text available
Since deep learning was introduced into super-resolution (SR), SR has achieved remarkable performance improvements. Since high-level features are more informative for reconstruction, most of SR methods have a lage number of parameters, which restrict their application in resource-constrained devices. Feedback mechanism makes it possible to get info...
Article
Full-text available
In recent years, numerous convolution neural networks (CNNs) for single image super-resolution (SISR) have shown powerful capability in image reconstruction. Especially, accurate and compact networks receive widespread attention due to their superiority in running speed on resources-limited devices. However, in most lightweight CNN-based methods, t...
Article
Full-text available
Aerial images are often applied into disaster area surveillance. High-resolution (HR) aerial images are preferred to monitor the disaster area since they can provide abundant information. However, limited by hardware device and imaging environment, the resolution of captured aerial images may not meet the needs of practical application. Image super...
Article
Full-text available
Due to limitations of the optical lenses, using the digital single-lens camera to obtain an all-in-focus image is difficult. In order to overcome this difficulty, a lot of multi-focus image fusion methods have been proposed to produce all-in-focus images. With the development of Deep Learning (DL), the Convolutional Neural Networks (CNNs) have been...
Article
Deep convolutional neural networks (CNN) have achieved remarkable performance in super-resolution (SR) recently. However, deep CNN-based methods are difficult to be utilized in embedded portable device due to their heavy computation and memory consumption. To solve the above problem, we propose an effective lightweight multi-scale feature extractio...
Article
Full-text available
Since the development of deep learning, image super-resolution (SR) has made great progress, and become the focus of academic research. Because high-level features are more informative for the reconstruction, most SR networks have a large number of layers and parameters, which restrict their application in resource-constrained devices. Recently, li...
Article
Full-text available
Accurate and fast facial feature learning is vital for Facial Expression Recognition (FER). Recent researches have proved that ensemble methods can perform efficiently and effectively on the FER, whereas these methods still confront the issues: incomplete information extraction of facial images and weak robustness on large-scale datasets. In this p...
Article
Full-text available
Recently, most existing learning-based fusion methods are not fully end-to-end, which still predict the decision map and recover the fused image by the refined decision map. However, in practice, these methods are hard to predict the decision map precisely. Inaccurate prediction further degrades the performance of fusing, resulting in edge blurring...
Article
The conjugate gradient (CG) method exhibits fast convergence speed than the steepest descent, which has received considerable attention. In this work, we propose two CG-based methods for nonlinear active noise control (NLANC). The proposed filtered-s Bessel CG (FsBCG)-I algorithm implements the functional link artificial neural network (FLANN) as a...
Preprint
We propose a novel M-estimate conjugate gradient (CG) algorithm, termed Tukey's biweight M-estimate CG (TbMCG), for system identification in impulsive noise environments. In particular, the TbMCG algorithm can achieve a faster convergence while retaining a reduced computational complexity as compared to the recursive least-squares (RLS) algorithm....
Article
Full-text available
Recently, using deep learning(DL) in super-resolution(SR) has ac- hieved great success. These methods combine the convolutional neural network(CNN) to learn a general matrix function for an end-to-end mapping. However, as the width and depth of the network increase, there are two essential problems in the SR tasks. On the one hand, a wider and deep...
Article
Full-text available
With the development of deep learning, convolution neural networks (CNNs) have drawn increasing attention in the field of single-image super-resolution (SISR). The previous methods have achieved excellent performance. However, in order to boost the performance, researchers often stack the basic blocks and deepen the networks, which leads to trainin...
Article
In recent years, numerous lightweight convolution neural networks (CNNs) have made remarkable progress for single image super-resolution (SISR) and showed great power for image reconstruction under constrained resources. However, existing lightweight networks can not fully utilize the informative hierarchical features, which will lead to the degrad...
Article
Full-text available
High resolution medical images are expected for accurate analysis results in medical diagnosis. However, the resolution of these medical images is always restricted by the factors such as medical devices, time constraints. Despite these restrictions, the resolution of these medical images can be enhanced with a well-designed super-resolution(SR) al...
Article
Full-text available
Recently, software architectures applied to physical agents have become a boost from the emerging Artificial Intelligence(AI). In these smart physical agents, simultaneously image information processing appears vital in particular. Single Image Super Resolution(SISR) serves as the foundation of the image process, presenting its prospects driven by...
Article
Recently, deep learning (DL) -based industrial applications have attracted broad attention due to their advanced performance. However, the limited computational resource in portable devices always makes big DL models inapplicable in the industry. DL-based Single Image Super-Resolution (SISR) also encounters this problem because of its large computa...
Article
Although the performance of pansharpening has been significantly improved by advanced deep-learning (DL) technologies in recent years, most DL-based methods fail to process multispectral (MS) images with arbitrary numbers of bands by a single model. Consequently, it is inevitable to train separate models for MS images with different numbers of band...
Preprint
Part I of this paper reviewed the development of the linear active noise control (ANC) technique in the past decade. However, ANC systems might have to deal with some nonlinear components and the performance of linear ANC techniques may degrade in this scenario. To overcome this limitation, nonlinear ANC (NLANC) algorithms were developed. In Part I...
Article
Full-text available
Real-time monitoring and surveillance play an important role in the field of remote sensing, where multi-spectral (MS) images with high spatial resolution are widely desired for better analysis. However, high-resolution MS images cannot be directly obtained due to the limitations of sensors and bandwidth. As an essential way to alleviate this probl...
Preprint
Active noise control (ANC) is an effective way for reducing the noise level in electroacoustic or electromechanical systems. Since its first introduction in 1936, this approach has been greatly developed. This paper focuses on discussing the development of ANC techniques over the past decade. Linear ANC algorithms, including the celebrated filtered...
Article
A theoretical model of temperature and stress damage of a triple-junction GaAs solar cell with a conical subwavelength structure antireflection film is proposed to analyze the influence of subwavelength structure on damage characteristics. The distribution of temperature and stress under different cone structure parameters are calculated. Results s...
Article
Convolutional neural networks (CNNs) have played a predominant role in the field of remote sensing over the last few years. As a significant branch of remote sensing image processing, pan-sharpening technique is to produce a high-resolution multi-spectral (HRMS) image based on a low-resolution multi-spectral (LRMS) image and a high-resolution (HR)...
Article
Full-text available
With the development of deep learning (DL), convolutional neural networks (CNNs) have shown great reconstruction performance in single image super-resolution (SISR). However, some methods blindly deepen the networks to purchase the performance, which neglect to make full use of the multi-scale information of different receptive fields and ignore th...
Article
Full-text available
In the past decade, single image super-resolution (SISR) based on convolutional neural networks (CNNs) has been represented remarkable performance. Powerful characterization of CNN is important for recent methods to learn an intricate non-linear mapping between high-resolution and corresponding low-resolution images. However, a deeper and wider net...
Article
Full-text available
Recently, numerous methods based on convolutional neural networks (CNNs) have been proposed to attain satisfactory performance in single image super-resolution (SISR). Meanwhile, diverse lightweight CNN-based networks have been proposed to achieve applicability in real-time scenarios. However, the receptive fields in lightweight networks are limite...
Article
Full-text available
Many scholars are committed to using deep learning methods to study facial expression recognition (FER). In recent years, FER has gradually been confined to psychology research in the early days to now involves knowledge of many disciplines such as physiology, psychology, cognition and medicine. With the extreme achievement of computer version tech...
Article
Full-text available
In recent years, convolutional neural network-based methods have achieved remarkable performance for the single-image super-resolution task. However, huge computational complexity and memory consumption of these methods limit their applications on the resource-constrained device. In this paper, we propose a lightweight network named one-shot aggreg...
Conference Paper
This paper studies the system identification problem using the q-least mean square (qLMS) algorithm. Particularly, the fuzzy-logic scheme is considered here. The proposed fuzzy-logic trained-qLMS (FLT-qLMS) algorithm is developed based on fuzzy-logic adapted, which averts the q value selection problem in practical applications. However, the perform...
Article
Due to limitation of optical lenses, obtaining all-in-focus images is difficult. However, lots of multi-focus image fusion methods cause undesirable artifacts around the focused and defocused boundaries in fusion images. Usually, these boundaries are at the edges of objects in images while the gradient information can reflect edge information intui...
Article
Full-text available
Deep-learning (DL)-based methods are of growing importance in the field of single image super-resolution (SISR). The practical application of these DL-based models is a remaining problem due to the requirement of heavy computation and huge storage resources. The powerful feature maps of hidden layers in convolutional neural networks (CNN) help the...
Article
Infrared (IR) and visible (VIS) image fusion technology combines the complementary information of the same scene from IR and VIS imaging sensors to generate a composite image, which is beneficial to post image-processing tasks. In order to achieve good fusion performance, a method by combining rolling guidance filter (RGF) and convolutional sparse...
Article
Full-text available
In recent years, deep convolutional neural networks have played an increasingly important role in single-image super-resolution (SR). However, with the increase of the depth and width of networks, the super-resolution methods based on convolution neural networks are facing training difficulties, memory consumption, running slowness and other proble...
Article
Knowledge distillation (KD) is a standard teacher-student learning framework to train a light-weight student network under the guidance of a well-trained, large teacher network. As an effective teaching strategy, interactive teaching has been widely employed at school to motivate students, in which teachers not only provide knowledge, but also give...
Article
Full-text available
Active noise control (ANC) is an effective way for reducing the noise level in electroacoustic or electromechanical systems. Since its first introduction in 1936, this approach has been greatly developed. This paper focuses on discussing the development of ANC techniques over the past decade. Linear ANC algorithms, including the celebrated filtered...
Article
Recently, a very deep convolutional neural network (CNN) has achieved impressive results in image super-resolution (SR). In particular, residual learning techniques are widely used. However, the previously proposed residual block can only extract one single-level semantic feature maps of one single receptive field. Therefore, it is necessary to sta...
Article
Imaging systems with different imaging sensors are widely applied to surveillance field, military field, and medicine field. Particularly, infrared imaging sensors can acquire thermal radiations emitted by different objects but lack textural details, and visible imaging sensors can capture abundant textural information but suffer from loss of scene...
Article
Data cognition plays an important role in cognitive computing. Cognition of low-resolution (LR) image is a long-stand problem because LR images have insufficient information about objects. For better cognition of LR images, a multi-resolution residual network (MRRN) is proposed to improve image resolution in this paper for cognitive computing syste...
Article
Full-text available
Acquiring all-in-focus images is significant in the multi-media era. Limited by the depth-of-field of the optical lens, it is hard to acquire an image with all targets are clear. One possible solution is to merge the information of a few complementary images in the same scene. In this article, we employ a two-channel convolutional network to derive...
Article
Full-text available
Ensemble clustering techniques have improved in recent years, offering better average performance between domains and data sets. Benefits range from finding novelty clustering which are unattainable by any single clustering algorithm to providing clustering stability, such that the quality is little affected by noise, outliers or sampling variation...
Article
Full-text available
Part I of this paper reviewed the development of the linear active noise control (ANC) technique in the past decade. However, ANC systems might have to deal with some nonlinear components and the performance of linear ANC techniques may degrade in this scenario. To overcome this limitation, nonlinear ANC (NLANC) algorithms were developed. In Part I...
Article
In recent years, deep convolutional neural networks (CNNs) have achieved a lot of outstanding results in super‐resolution with superior ability. However, the majority of CNNs only use a series of convolution kernels with the same size to extract features. This will cause limited receptive fields. In this work, we propose a parallel convolution atte...
Article
Based on the randomness of spontaneous emission, the statistical characteristics of phase noise are discussed. A theoretical analysis model, focusing on the amplitude randomness of spontaneous emission, is established to calculate laser phase noise. Then, the coherence of a laser before and after phase-locked control is calculated when an ideal las...
Article
Thermal infrared (IR) images are widely used in smart grids for numerous applications. These applications prefer high-resolution (HR) IR images since HR IR images benefit the performance. However, HR IR imaging devices are extremely expensive. To save the cost of upgrading imaging devices, an iterative error reconstruction network (IERN) is propose...
Article
Image fusion is an important task for computer vision as a diverse range of applications are benefiting from the fusion operation. The existing image fusion methods are largely implemented at the pixel level, which may introduce artifacts and/or inconsistencies while the computational complexity is relatively high. In this paper, we propose a symme...
Article
Full-text available
The below affiliation for author Chi Yang was missed to be included in the original article.
Preprint
Full-text available
Knowledge distillation is a standard teacher-student learning framework to train a light-weight student network under the guidance of a well-trained large teacher network. As an effective teaching strategy, interactive teaching has been widely employed at school to motivate students, in which teachers not only provide knowledge but also give constr...
Article
Full-text available
High-resolution multi-spectral images are desired for applications in remote sensing. However, multi-spectral images can only be provided in low resolutions by optical remote sensing satellites. The technique of pan-sharpening wants to generate high-resolution multi-spectral (MS) images based on a panchromatic (PAN) image and the low-resolution cou...
Article
High-resolution (HR) medical images are preferred in clinical diagnoses and subsequent analysis. However, the acquisition of HR medical images is easily affected by hardware devices. As an effective and trusted alternative method, the super-resolution (SR) technology is introduced to improve the image resolution. Compared with traditional SR method...
Article
Full-text available
Since the limitation of optical sensors, it’s often hard to obtain an image with the ideal resolution. Image super-resolution (SR) technology can generate a high-resolution image from the corresponding low-resolution image. Recently, deep learning (DL) based SR methods draw much attention due to their satisfying reconstruction results. However, the...
Article
Full-text available
The limitation of optical sensors set a challenge to acquire high resolution (HR) images. Previous sparse coding-based SR methods fail to reconstruct satisfied high resolution image due to three problems. First, sparse representation calculation is time consuming, which restricts its application in real-time systems. Second, sparse coding-based SR...
Article
Full-text available
Chinese Government has launched ambitious healthcare reform aiming to provide better healthcare services for both urban and rural residents via remote diagnosis. Recently, the requirement of high-resolution (HR) images becomes more urgent in the medical field, especially for remote diagnosis. Remote diagnosis is an important means of the Internet o...
Article
Full-text available
In this paper, we propose a modified version of exponential cost function to improve the stability of adaptive algorithm, where the recursive algorithm is based on the Dawson function. The second-order Volterra (SOV) filter is incorporated into the proposed recursive algorithm, resulting the SOV-ExRLS algorithm, to achieve the improved performance...
Article
A thermal damage analysis model of metal components with surface microstructure under laser irradiation is established. In order to ensure the influence law, the surface microstructure of metal component is simplified to periodic patterns. The light field and temperature distribution on the metal surface are calculated. And then the damage threshol...