Learning the non-linear image upscaling process has previously been considered as a simple regression process, where various models have been utilized to describe the correlations between high-resolution (HR) and low-...
详细信息
ISBN:
(纸本)9781479983407
Learning the non-linear image upscaling process has previously been considered as a simple regression process, where various models have been utilized to describe the correlations between high-resolution (HR) and low-resolution (LR) images/patches. In this paper, we present a multitask learning framework based on deep neural network for image super-resolution, where we jointly consider the image super-resolution process and the image degeneration process. By sharing parameters between the two highly relevant tasks, the proposed framework could effectively improve the obtained neural network based mapping model between HR and L-R image patches. Experimental results have demonstrated clear visual improvement and high computational efficiency, especially with large magnification factors.
The present paper aims to propose a new type of learning method to increase information content in input patterns with multiple steps to be used in supervised learning. Unsupervised pre-training to train multi-layered...
详细信息
ISBN:
(纸本)9781538674482;9781538674475
The present paper aims to propose a new type of learning method to increase information content in input patterns with multiple steps to be used in supervised learning. Unsupervised pre-training to train multi-layered neural networks turned out to be not so effective as has been expected, because connection weights obtained by the unsupervised learning tend to lose their original characteristics immediately in supervised training. To keep original information by unsupervised learning, we here try to increase information in input patterns as much as possible to overcome the vanishing information problem. In particular, for acquiring detailed information more appropriately, we gradually increases detailed information through multiple steps. We applied the method to the actual real data set of the eye-tracking, and two step information augmentation approach was taken. The results confirmed that generalization performance could be improved. In addition, we could interpret the importance of input variables more easily by treating all connection weights collectively.
Face identification from low quality and low resolution Near-Infrared (NIR) face images is a challenging problem. Since surveillance cameras typically acquire images at a large standoff distance, the effective resolut...
详细信息
ISBN:
(纸本)9781467399623
Face identification from low quality and low resolution Near-Infrared (NIR) face images is a challenging problem. Since surveillance cameras typically acquire images at a large standoff distance, the effective resolution of the face is not large enough to identify the individuals. Moreover for a 24-hour surveillance footage, images in low light and at nighttime are acquired in NIR mode which makes the identification problem even more challenging. We propose an effective method using both hand-crafted and learned features for face identification of low resolution NIR images. We show that learned features contribute considerably to the performance of identification algorithm, and that using both feature level and score level fusion in a hierarchal approach gives good performance. The results demonstrate the effectiveness of the proposed approach on images which are of low quality, low resolution and acquired under challenging illumination conditions in near-infrared mode by surveillance cameras.
Due to the complexity of modern industrial processes, there may be both linear and nonlinear relationships exist among process variables. In addition, the dynamic behavior of the process also brings challenges to proc...
详细信息
Due to the complexity of modern industrial processes, there may be both linear and nonlinear relationships exist among process variables. In addition, the dynamic behavior of the process also brings challenges to process ***, some linear monitoring methods have been developed for dynamic processes. However, the existing methods can not precisely extract the dynamic characteristics of nonlinear processes. What is more, purely linear or nonlinear methods can hardly tackle the hybrid linear and nonlinear relationships among process variables. To address the above issue, a novel method, termed slow feature networks(SFNet) is proposed and applied for dynamic process monitoring. On the one hand, a slowly varying constraint of hidden features is added to the autoencoder, so that the static and dynamic characteristics of nonlinear processes can be extracted concurrently. On the other hand, a linear mapping is incorporated into the nonlinear neural network structure,thereby providing parallel analysis of linear and nonlinear monitoring information. Five statistics are constructed for comprehensive process monitoring from both static and dynamic, linear and nonlinear perspectives. In this way, alarms corresponding to different statistical information are used to indicate different operating statuses with meaningful interpretation and enhanced process understanding. A real industrial example is adopted to validate the performance of the proposed method.
Two data-driven approaches based on the Fourier-transform infrared spectroscopy (FTIR) data are presented in this work to predict crude oil properties. The first approach is the combination of the principal component ...
详细信息
Two data-driven approaches based on the Fourier-transform infrared spectroscopy (FTIR) data are presented in this work to predict crude oil properties. The first approach is the combination of the principal component analysis (PCA) and the support vector regression (SVR), namely PCA-SVR. In the PCA-SVR, the PCA is employed to extract the high-dimension FTIR data to obtain lower-dimensional data. The lower-dimensional data is utilized as the inputs of the SVR to predict crude oil properties. The second approach is a hybrid model composed of the autoencoder and the SVR, namely Auto-SVR. In the Auto-SVR, the autoencoder is exploited to learn new representations for the dimensionality reduction of the FTIR data. The learned lower-dimensional representations are input into the SVR to predict crude oil properties. The presented data-driven approaches are used to predict fractions of light virgin naphtha (LVN), heavy virgin naphtha (HVN), kerosene (Kero), distillate, vacuum gas oil (VGO), and residual in crude oil. According to the obtained results, the presented methods can achieve accurate predictions with satisfactory prediction accuracy.
Audio Word2Vec offers vector representations of fixed dimensionality for variable-length audio segments using Sequence to-sequence autoencoder (SA). These vector representations are shown to describe the sequential ph...
详细信息
ISBN:
(纸本)9781538646595
Audio Word2Vec offers vector representations of fixed dimensionality for variable-length audio segments using Sequence to-sequence autoencoder (SA). These vector representations are shown to describe the sequential phonetic structures of the audio segments to a good degree, with real world applications such as spoken term detection (STD). This paper examines the capability of language transfer of Audio Word2Vec. We train SA from one language (source language) and use it to extract the vector representation of the audio segments of another language (target language). We found that SA can still catch the phonetic structure from the audio segments of the target language if the source and target languages are similar. In STD, we obtain the vector representations from the SA learned from a large amount of source language data, and found them surpass the representations from naive encoder and SA directly learned from a small amount of target language data. The result shows that it is possible to learn Audio Word2Vec model from high-resource languages and use it on low-resource languages. This further expands the usability of Audio Word2Vec.
暂无评论