Virtual View Generation Based on 3D-Dense-Attentive GAN Networks

Fu, Junwei; Liang, Jun

doi:10.3390/s19020344

Cited by 4 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another interesting line of exploration would be to utilise multi-task learning for exploiting complementarities in (substantially available) cross-sectional and (sparse) longitudinal data for improving prediction accuracy as in [77]. We will also investigate architectures alternative to SAGAN such as Dense-Attentive GAN [78].…”

Section: Discussionmentioning

confidence: 99%

Outlier-Based Autism Detection Using Longitudinal Structural MRI

et al. 2022

View full text Add to dashboard Cite

Diagnosis of Autism Spectrum Disorder (ASD) using clinical evaluation (cognitive tests) is challenging due to wide variations amongst individuals. Since no effective treatment exists, prompt and reliable ASD diagnosis can enable the effective preparation of treatment regimens. This paper proposes structural Magnetic Resonance Imaging (sMRI)-based ASD diagnosis via an outlier detection approach. To learn spatio-temporal patterns in structural brain connectivity, a Generative Adversarial Network (GAN) is trained exclusively with sMRI scans of healthy subjects. Given a stack of three adjacent slices as input, the GAN generator reconstructs the next three adjacent slices; the GAN discriminator then identifies ASD sMRI scan reconstructions as outliers. This model is compared against two other baselines-a simpler UNet and a sophisticated Self-Attention GAN. Axial, Coronal and Sagittal sMRI slices from the multi-site ABIDE II dataset are used for evaluation. Extensive experiments reveal that our ASD detection framework performs comparably with the state-of-the-art with far fewer training data. Furthermore, longitudinal data (two scans per subject over time) achieve 17-28% higher accuracy than cross-sectional data (one scan per subject). Among other findings, metrics employed for model training as well as reconstruction loss computation impact detection performance, and the coronal modality is found to best encode structural information for ASD detection.

show abstract

Section: Discussionmentioning

confidence: 99%

Outlier-Based Autism Detection Using Longitudinal Structural MRI

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Studies showed that the training time of traditional convolutional neural networks was too long, the accuracy was not ideal, and could not get diversified image features. Gradient dispersion would be generated in the process of backpropagation [42][43][44][45]. Based on these studies, we designed a multi-scale high-density convolutional neural network based on the multi-scale convolutional neural network and Densenet structure.…”

Section: H Performance Analysis Of Mhcnnmentioning

confidence: 99%

Task-State EEG Signal Classification for Spatial Cognitive Evaluation Based on Multiscale High-Density Convolutional Neural Network

Dong

Tang

et al. 2022

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

In this study, a multi-scale high-density convolutional neural network (MHCNN) classification method for spatial cognitive ability assessment was proposed, aiming at achieving the binary classification of task-state EEG signals before and after spatial cognitive training. Besides, the multi-dimensional conditional mutual information method was used to extract the frequency band features of the EEG data. And the coupling features under the combination of multi-frequency bands were transformed into multi-spectral images. At the same time, the idea of Densenet was introduced to improve the multi-scale convolutional neural network. Firstly, according to the discreteness of multispectral EEG image features, two-scale convolution kernels were used to calculate and learn useful channel and frequency band feature information in multispectral image data. Secondly, to enhance feature propagation and reduce the number of parameters, the dense network was connected after the multi-scale convolutional network, and the learning rate change function of the stochastic gradient descent algorithm was optimized to objectively evaluate the training effect. The experimental results showed that compared with the classical convolution neural network (CNN) and multi-scale convolution neural network, the proposed MHCNN had better classification Manuscript received November 12, 2021.

show abstract

“…Geng et al [33] proposed an unsupervised learning framework, which adds training constraints for the depth estimation task. Fu et al [34] proposed a virtual view-generation algorithm based on GAN to improve the performance of binocular vision systems. Moreover, some researchers used GAN to perform unsupervised adversarial transfer learning.…”

Section: Gan-based Unsupervised Learningmentioning

confidence: 99%

A novel vSLAM framework with unsupervised semantic segmentation based on adversarial transfer learning

Jin

Chen

Sun

et al. 2020

Applied Soft Computing

View full text Add to dashboard Cite

Significant progress has been made in the field of visual Simultaneous Localization and Mapping (vSLAM) systems. However, the localization accuracy of vSLAM can be significantly reduced in dynamic applications with mobile robots or passengers. In this paper, a novel semantic SLAM framework in dynamic environments is proposed to improve the localization accuracy. We incorporate a semantic segmentation model into the Oriented FAST and Rotated BRIEF-SLAM2 (ORB-SLAM2) system to filter out dynamic feature points, but we encounter one main challenge, i.e. the performance of a segmentation network well-trained with labeled datasets may decrease seriously in a real application without any labeled data due to the inconsistency between the source domain and the target domain. Therefore, we proposed an unsupervised semantic segmentation model with a Residual Neural Network (ResNet) structure, which is trained by the adversarial transfer learning method in the multi-level feature spaces. This work may be the first to perform multi-level feature space adversarial transfer learning for the semantic SLAM task in dynamic environments. In order to evaluate our method, images of indoor scenes from three datasets are used as the source domain, and the dynamic sequences of the TUM dataset are used as the target domain. The extensive experimental results show favorable performance against the state-of-the-art methods in terms of the absolute trajectory accuracy and image semantic segmentation quality.

show abstract

Virtual View Generation Based on 3D-Dense-Attentive GAN Networks

Cited by 4 publications

References 39 publications

Outlier-Based Autism Detection Using Longitudinal Structural MRI

Outlier-Based Autism Detection Using Longitudinal Structural MRI

Task-State EEG Signal Classification for Spatial Cognitive Evaluation Based on Multiscale High-Density Convolutional Neural Network

A novel vSLAM framework with unsupervised semantic segmentation based on adversarial transfer learning

Contact Info

Product

Resources

About