A Novel Manifold Regularized Online Semi-supervised Learning Model

Ding, Shuguang; Xi, Xuekui; Li, Yong; Qiao, Hong; Zhang, Bo

doi:10.1007/s12559-017-9489-x

Cited by 15 publications

(9 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, the SOM is used for both feature extraction and pattern classification. Using the three layers of neural network in the hierarchical action recognition architecture introduces an online semi-supervised learning model (Ding et al 2017), which resembles the human learning process in which the training samples are often obtained successively. In this way, the observations arrive in sequence and the corresponding labels are presented very sporadically.…”

Section: Proposed Approach For Online Action Recognitionmentioning

confidence: 99%

Online recognition of unsegmented actions with hierarchical SOM architecture

Gharaee

2020

Cogn Process

View full text Add to dashboard Cite

Automatic recognition of an online series of unsegmented actions requires a method for segmentation that determines when an action starts and when it ends. In this paper, a novel approach for recognizing unsegmented actions in online test experiments is proposed. The method uses self-organizing neural networks to build a three-layer cognitive architecture. The unique features of an action sequence are represented as a series of elicited key activations by the first-layer self-organizing map. An average length of a key activation vector is calculated for all action sequences in a training set and adjusted in learning trials to generate input patterns to the second-layer self-organizing map. The pattern vectors are clustered in the second layer, and the clusters are then labeled by an action identity in the third layer neural network. The experiment results show that although the performance drops slightly in online experiments compared to the offline tests, the ability of the proposed architecture to deal with the unsegmented action sequences as well as the online performance makes the system more plausible and practical in real-case scenarios.

show abstract

Section: Proposed Approach For Online Action Recognitionmentioning

confidence: 99%

Online recognition of unsegmented actions with hierarchical SOM architecture

Gharaee

2020

Cogn Process

View full text Add to dashboard Cite

show abstract

“…This network is called dual flow subspace network (DFSNet), due to its flexibility in handling both learning paradigms. In addition to its advantages, semi-supervised learning is of theoretical interest, since it makes it possible to understand the mechanisms of human learning [46,47].…”

Section: Introductionmentioning

confidence: 99%

A semi-supervised convolutional neural network based on subspace representation for image classification

Gatto

Souza

Santos

et al. 2020

J Image Video Proc.

View full text Add to dashboard Cite

This work presents a shallow network based on subspaces with applications in image classification. Recently, shallow networks based on PCA filter banks have been employed to solve many computer vision-related problems including texture classification, face recognition, and scene understanding. These approaches are robust, with a straightforward implementation that enables fast prototyping of practical applications. However, these architectures employ either unsupervised or supervised learning. As a result, they may not achieve highly discriminative features in more complicated computer vision problems containing variations in camera motion, object's appearance, pose, scale, and texture, due to drawbacks related to each learning paradigm. To cope with this disadvantage, we propose a semi-supervised shallow network equipped with both unsupervised and supervised filter banks, presenting representative and discriminative abilities. Besides, the introduced architecture is flexible, performing favorably on different applications whose amount of supervised data is an issue, making it an attractive choice in practice. The proposed network is evaluated on five datasets. The results show improvement in terms of prediction rate, comparing to current shallow networks.

show abstract

“…Lv et al proposed a semi-supervised predictive sparse decomposition method for feature learning [27]. To solve the online semi-supervised learning problems, Ding et al proposed a novel manifold regularized model in a reproducing kernel Hilbert space [28].…”

Section: Introductionmentioning

confidence: 99%

A Novel Semi-Supervised Convolutional Neural Network Method for Synthetic Aperture Radar Image Recognition

et al. 2019

View full text Add to dashboard Cite

Background / introduction: SAR image automatic target recognition technology (SAR-ATR) is one of the research hotspots in the field of image cognitive learning. Inspired by the human cognitive process, experts have designed convolutional neural networks (CNN) based methods and successfully applied the methods to SAR-ATR. However, the performance of CNNs significantly deteriorates when the labelled samples are insufficient. Methods: To effectively utilize the unlabelled samples, a semi-supervised CNN method is proposed in this paper. First, CNN is used to extract the features of the samples, and subsequently the class probabilities of the unlabelled samples are computed using the softmax function. To improve the effectiveness of the unlabelled samples, we remove possible noise performing thresholding on the class probabilities. Afterwards, based on the remaining class probabilities, the information contained in the unlabelled samples is integrated with the scatter matrices of the standard linear discriminant analysis (LDA) method. The loss function of CNN consists of a supervised component and an unsupervised component, where the supervised component is created using the cross-entropy function and the unsupervised component is created using the scatter matrices. The class probabilities are utilized to control the impact of the unlabelled samples in the training process, and the reliability of the unlabelled samples is further improved. Results: We choose ten types of targets from the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset. The experimental results show that the recognition accuracy of 2 our method is significantly higher than that of the supervised CNN method. Conclusions: It proves that our method can effectively improve the SAR-ATR accuracy despite the deficiency of the labelled samples.

show abstract

A Novel Manifold Regularized Online Semi-supervised Learning Model

Cited by 15 publications

References 31 publications

Online recognition of unsegmented actions with hierarchical SOM architecture

Online recognition of unsegmented actions with hierarchical SOM architecture

A semi-supervised convolutional neural network based on subspace representation for image classification

A Novel Semi-Supervised Convolutional Neural Network Method for Synthetic Aperture Radar Image Recognition

Contact Info

Product

Resources

About