In this paper, we present a novel deep learning model termed Deep Autoencoding-Classification Network (DACN) for HEp-2 cell classification. The DACN consists of an au-toencoder and a normal classification convolutiona...
详细信息
ISBN:
(纸本)9781509011735
In this paper, we present a novel deep learning model termed Deep Autoencoding-Classification Network (DACN) for HEp-2 cell classification. The DACN consists of an au-toencoder and a normal classification convolutional neural network (CNN), while the two architectures shares the same encoding pipeline. The DACN model is jointly optimized for the classification error and the image reconstruction error based on a multi-task learning procedure. We evaluate the proposed model using the publicly available ICPR2012 benchmark dataset. We show that this architecture is particularly effective when the training dataset is small which is often the case in medical imaging applications. We present experimental results to show that the proposed approach outperforms all known state of the art HEp-2 cell classification methods.
We present a framework to synthesize character movements based on high level parameters, such that the produced movements respect the manifold of human motion, trained on a large motion capture dataset. The learned mo...
详细信息
We present a framework to synthesize character movements based on high level parameters, such that the produced movements respect the manifold of human motion, trained on a large motion capture dataset. The learned motion manifold, which is represented by the hidden units of a convolutional autoencoder, represents motion data in sparse components which can be combined to produce a wide range of complex movements. To map from high level parameters to the motion manifold, we stack a deep feedforward neural network on top of the trained autoencoder. This network is trained to produce realistic motion sequences from parameters such as a curve over the terrain that the character should follow, or a target location for punching and kicking. The feedforward control network and the motion manifold are trained independently, allowing the user to easily switch between feedforward networks according to the desired interface, without re-training the motion manifold. Once motion is generated it can be edited by performing optimization in the space of the motion manifold. This allows for imposing kinematic constraints, or transforming the style of the motion, while ensuring the edited motion remains natural. As a result, the system can produce smooth, high quality motion sequences without any manual pre-processing of the training data.
Fabric defect detection have importance in terms of sectoral quality. Automatic systems are developed on the defect detection, in this regard many methods are tried to obtain high precision with image processing studi...
详细信息
ISBN:
(纸本)9781509016792
Fabric defect detection have importance in terms of sectoral quality. Automatic systems are developed on the defect detection, in this regard many methods are tried to obtain high precision with image processing studies. In this study, deep learning which distinguishes with multi-layer architectures and reveals high achievement is applied to fabric defect detection. autoencoder - a deep learning algorithm-that aimed to represent input data via compression or decompression is tried to detect defect of fabrics and it gains acceptable success. The vital goal of this study is to increase achievement of feature extraction by tuning up the autoencoder's input value and hyper parameters.
We propose a novel Deep learning approach using autoencoders to map spectral bands to a space of lower dimensionality while preserving the information that makes it possible to discriminate different materials. Deep l...
详细信息
ISBN:
(纸本)9781510603806;9781510603813
We propose a novel Deep learning approach using autoencoders to map spectral bands to a space of lower dimensionality while preserving the information that makes it possible to discriminate different materials. Deep learning is a relatively new pattern recognition approach which has given promising result in many applications. In Deep learning a hierarchical representation of increasing level of abstraction of the features is learned. autoencoder is an important unsupervised technique frequently used in Deep learning for extracting important properties of the data. The learned latent representation is a non-linear mapping of the original data which potentially preserve the discrimination capacity.
The preprocessing procedure for anomalous behavior of robot system elements is proposed in the paper. It uses a special kind of a neural network called an autoencoder to solve two problems. The first problem is to dec...
详细信息
The preprocessing procedure for anomalous behavior of robot system elements is proposed in the paper. It uses a special kind of a neural network called an autoencoder to solve two problems. The first problem is to decrease the dimensionality of the training data using the autoencoder to calculate the Mahalanobis distance, which can be viewed as one of the best metrics to detect the anomalous behavior of robots or sensors in the robot systems. The second problem is to apply the autoencoder to transfer learning. The autoencoder is trained by means of the target data which corresponds to the extreme operational conditions of the robot system. The source data containing the normal and anomalous observations derived from the normal operation conditions is reconstructed to the target data using the trained autoencoder. The reconstructed source data is used to define a optimal threshold for making decision on the anomaly of the observation based on the Mahalanobis distance.
Automatic semantic annotation of high-resolution optical satellite images is a task to assign one or several predefined semantic concepts to an image according to its content. The fundamental challenge arises from the...
详细信息
ISBN:
(纸本)9781509033324
Automatic semantic annotation of high-resolution optical satellite images is a task to assign one or several predefined semantic concepts to an image according to its content. The fundamental challenge arises from the difficulty of characterizing complex and ambiguous contents of the satellite images. To address this challenge, a diversity constrained joint multi-feature learning method is proposed to learn robust feature representations for annotating satellite images. The key motivation of our method is to make full use of the complementarity diversity information among the heterogeneous features in the learning process. Comprehensive experiments on an annotation dataset demonstrate the superiority and effectiveness of our method compared with baseline multi-feature learning method.
In this paper, we present a Conditional Random Field (CRF) model to deal with the problem of segmenting handwritten historical document images into different regions. We consider page segmentation as a pixel-labeling ...
详细信息
ISBN:
(纸本)9781509009817
In this paper, we present a Conditional Random Field (CRF) model to deal with the problem of segmenting handwritten historical document images into different regions. We consider page segmentation as a pixel-labeling problem, i.e., each pixel is assigned to one of a set of labels. Features are learned from pixel intensity values with stacked convolutional autoencoders in an unsupervised manner. The features are used for the purpose of initial classification with a multilayer perceptron. Then a CRF model is introduced for modeling the local and contextual information jointly in order to improve the segmentation. For the purpose of decreasing the time complexity, we perform labeling at superpixel level. In the CRF model, graph nodes are represented by superpixels. The label of each pixel is determined by the label of the superpixel to which it belongs. Experiments on three public datasets demonstrate that, compared to previous methods, the proposed method achieves more accurate segmentation results and is much faster.
Fraud detection in electricity consumption is a major challenge for power distribution companies. While many pattern recognition techniques have been applied to identify electricity theft, they often require extensive...
详细信息
ISBN:
(纸本)9781509061679
Fraud detection in electricity consumption is a major challenge for power distribution companies. While many pattern recognition techniques have been applied to identify electricity theft, they often require extensive handcrafted feature engineering. Instead, through deep layers of transformation, nonlinearity, and abstraction, Deep Learning (DL) automatically extracts key features from data. In this paper, we design spatial and temporal deep learning solutions to identify nontechnical power losses (NTL), including Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) and Stacked autoencoder. These models are evaluated in a modified IEEE 123-bus test feeder. For the same tests, we also conduct comparison experiments using three conventional machine learning approaches: Random Forest, Decision Trees and shallow Neural Networks. Experimental results demonstrate that the spatiotemporal deep learning approaches outperform conventional machine learning approaches.
暂无评论