3D face reconstruction from a 2D face image has been found important to various applications such as face detection and recognition because a 3D face provides more semantic information than 2D image. This paper propos...
详细信息
3D face reconstruction from a 2D face image has been found important to various applications such as face detection and recognition because a 3D face provides more semantic information than 2D image. This paper proposes a deep learning framework for 3D face reconstruction. The framework is designed to compute subspace feature of arbitrary face image, then map the feature to its counterpart in another subspace learned with 3D faces, and reconstruct the 3D face using the counterpart feature. During the course of training, we learn 2D and 3D subspaces through stacked contractive autoencoders (SCAE), use a one-layer fully connected neural network to learn the mapping, and use the pre-trained parameters of the SCAEs and the one-layer network to initialize a deep feedforward neural network whose input are face images and output are 3D faces. The network is optimized by gradient descent algorithm with back-propagation. Extensive experimental results on various data sets indicate the effectiveness of the proposed SCAE-based 3D face reconstruction method. (C) 2017 Elsevier B.V. All rights reserved.
Software defect prediction plays an important role in software quality ***,the performance of the prediction model is susceptible to the irrelevant and redundant *** addition,previous studies mostly regard software de...
详细信息
Software defect prediction plays an important role in software quality ***,the performance of the prediction model is susceptible to the irrelevant and redundant *** addition,previous studies mostly regard software defect prediction as a single objective optimization problem,and multi-objective software defect prediction has not been thoroughly *** the above two reasons,we propose the following solutions in this paper:(1)we leverage an advanced deep neural network-stacked contractive autoencoder(SCAE)to extract the robust deep semantic features from the original defect features,which has stronger discrimination capacity for different classes(defective or non-defective).(2)we propose a novel multi-objective defect prediction model named SMONGE that utilizes the Multi-Objective NSGAII algorithm to optimize the advanced neural network-Extreme learning machine(ELM)based on state-of-the-art Pareto optimal solutions according to the features extracted by *** mainly consider two *** objective is to maximize the performance of ELM,which refers to the benefit of the SMONGE *** objective is to minimize the output weight norm of ELM,which is related to the cost of the SMONGE *** compare the SCAE with six state-of-the-art feature extraction methods and compare the SMONGE model with multiple baseline models that contain four classic defect predictors and the MONGE model without SCAE across 20 open source software *** experimental results verify that the superiority of SCAE and SMONGE on seven evaluation metrics.
The rapid development of deep learning has promoted the application of rolling bearing fault diagnosis techniques. However, in practical applications, the researchers often faces the challenge of a serious imbalance i...
详细信息
The rapid development of deep learning has promoted the application of rolling bearing fault diagnosis techniques. However, in practical applications, the researchers often faces the challenge of a serious imbalance in the proportion of normal and fault states. This imbalance greatly affects the accuracy of diagnosis. Therefore, this paper proposes a novel fault diagnosis framework based on an auxiliary classifier generative adversarial network (ACGAN). Firstly, the stacked contractive autoencoder is cleverly combined with the discriminator network to improve its feature extraction capability and fault diagnosis accuracy. Subsequently, the original algorithm's focus on different types of samples is optimised to improve the generalisation of the diagnostic network. Finally, the stability of the generator network training is optimised with the help of the metric properties of the Kullback-Leibler scatter, and thus the variational stackedcontractive-ACGAN model is proposed. The experimental results show that the fault diagnosis accuracy reaches 99.75 % with 200 training samples of each class on the Case Western Reserve University (CWRU) bearing dataset, which is significantly better than other algorithms. Under the same conditions, on the Jiangnan University bearing dataset, the accuracy reaches 99.25 %, which shows good generalization and provides a broad prospect for future applications.
In this paper we propose a multimodal feature learning mechanism based on deep networks (i.e., stacked contractive autoencoders) for video classification. Considering the three modalities in video, i.e., image, audio ...
详细信息
In this paper we propose a multimodal feature learning mechanism based on deep networks (i.e., stacked contractive autoencoders) for video classification. Considering the three modalities in video, i.e., image, audio and text, we first build one stacked contractive autoencoder (SCAE) for each single modality, whose outputs will be joint together and fed into another Multimodal stacked contractive autoencoder (MSCAE). The first stage preserves intra-modality semantic relations and the second stage discovers inter-modality semantic correlations. Experiments on real world dataset demonstrate that the proposed approach achieves better performance compared with the state-of-the-art methods. (C) 2015 Elsevier B.V. All rights reserved.
暂无评论