Unsupervised domain adaptation for speech emotion recognition using PCANet

Huang, Zheng-Wei; Xue, Wei; Mao, Qirong; Zhan, Yongzhao

doi:10.1007/s11042-016-3354-x

Cited by 55 publications

(29 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used the same architecture and network settings as in Huang et al . () for implementation of the DLDI. Another method used in comparisons was the deep domain adaptation (DDA) (Glorot et al ., ), which employes both training data and testing data in two domains to pretrain the network in an unsupervised manner.…”

Section: Discussionmentioning

confidence: 99%

“…The DLDI explicitly captures the incremental information along the interpolating path between the source domain and the target domain (Chopra & Gopalan, 2013). We used the same architecture and network settings as in Huang et al (2017) for implementation of the DLDI. Another method used in comparisons was the deep domain adaptation (DDA) (Glorot et al, 2011), which employes both training data and testing data in two domains to pretrain the network in an unsupervised manner.…”

Section: Comparisons With Some Other Deep Domain Adaptation Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Classify epithelium‐stroma in histopathological images based on deep transferable network

Zheng

Liu

et al. 2018

Journal of Microscopy

View full text Add to dashboard Cite

Recently, the deep learning methods have received more attention in histopathological image analysis. However, the traditional deep learning methods assume that training data and test data have the same distributions, which causes certain limitations in real-world histopathological applications. However, it is costly to recollect a large amount of labeled histology data to train a new neural network for each specified image acquisition procedure even for similar tasks. In this paper, an unsupervised domain adaptation is introduced into a typical deep convolutional neural network (CNN) model to mitigate the repeating of the labels. The unsupervised domain adaptation is implemented by adding two regularisation terms, namely the feature-based adaptation and entropy minimisation, to the object function of a widely used CNN model called the AlexNet. Three independent public epithelium-stroma datasets were used to verify the proposed method. The experimental results have demonstrated that in the epithelium-stroma classification, the proposed method can achieve better performance than the commonly used deep learning methods and some existing deep domain adaptation methods. Therefore, the proposed method can be considered as a better option for the real-world applications of histopathological image analysis because there is no requirement for recollection of large-scale labeled data for every specified domain.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Comparisons With Some Other Deep Domain Adaptation Methodsmentioning

confidence: 99%

Classify epithelium‐stroma in histopathological images based on deep transferable network

Zheng

Liu

et al. 2018

Journal of Microscopy

View full text Add to dashboard Cite

show abstract

“…It is a linear network for classification consisting of two stages where the weights are fixed and computed using PCA filters, which considerably reduces the computational cost. In [25], and based on the basic structure of PCANet, the authors apply DA for speech emotion recognition using three parallel networks with a different input for each one: source, target and a mixture of source and target. Once the three networks computed their own weights, the ones belonging to both the source and mixture networks are readjusted using the weights computed over the target network.…”

Section: Related Workmentioning

confidence: 99%

TCANet for Domain Adaptation of Hyperspectral Images

2019

View full text Add to dashboard Cite

The use of Convolutional Neural Networks (CNNs) to solve Domain Adaptation (DA) image classification problems in the context of remote sensing has proven to provide good results but at high computational cost. To avoid this problem, a deep learning network for DA in remote sensing hyperspectral images called TCANet is proposed. As a standard CNN, TCANet consists of several stages built based on convolutional filters that operate on patches of the hyperspectral image. Unlike the former, the coefficients of the filter are obtained through Transfer Component Analysis (TCA). This approach has two advantages: firstly, TCANet does not require training based on backpropagation, since TCA is itself a learning method that obtains the filter coefficients directly from the input data. Second, DA is performed on the fly since TCA, in addition to performing dimensional reduction, obtains components that minimize the difference in distributions of data in the different domains corresponding to the source and target images. To build an operating scheme, TCANet includes an initial stage that exploits the spatial information by providing patches around each sample as input data to the network. An output stage performing feature extraction that introduces sufficient invariance and robustness in the final features is also included. Since TCA is sensitive to normalization, to reduce the difference between source and target domains, a previous unsupervised domain shift minimization algorithm consisting of applying conditional correlation alignment (CCA) is conditionally applied. The results of a classification scheme based on CCA and TCANet show that the DA technique proposed outperforms other more complex DA techniques.

show abstract

“…Adopting the simple architecture of ScatNet and the robust performance of multi-layer CNNs, PCANet is fast to train, and invariant to intra-class variability. PCANet has proven its usage in applications like speech emotion recognition [10], human fall detection [11], vehicle make recognition [12], and so on.…”

Section: Related Workmentioning

confidence: 99%

VLSI design of a power-efficient object detector using PCANet

Zhou

Huang

2018

IEICE Electron. Express

View full text Add to dashboard Cite

This paper presents the hardware architecture and VLSI implementations of a PCANet-based object detector. The proposed PCANet model, cascaded with a linear support vector machine, can achieve better classification performance than traditional handcrafted computer vision methods, yet it is significantly more power efficient than multi-layer convolutional neural networks. The proposed pipeline hardware architecture, when implemented using Synopsys 32 nm process technology, results in 27.4 fps while processing 1080P, with only 0.5 watt power consumption. Targeted for the application of advanced driver assistance system, the proposed design is evaluated on road marking and traffic light dataset with an accuracy result of 96.8% and 93.1% respectively. Therefore, the proposed VLSI implementation of PCANet algorithm provides a high-throughput and power-efficient solution for object detection applications.

show abstract

Unsupervised domain adaptation for speech emotion recognition using PCANet

Cited by 55 publications

References 26 publications

Classify epithelium‐stroma in histopathological images based on deep transferable network

Classify epithelium‐stroma in histopathological images based on deep transferable network

TCANet for Domain Adaptation of Hyperspectral Images

VLSI design of a power-efficient object detector using PCANet

Contact Info

Product

Resources

About