Multi-adversarial Variational Autoencoder Networks

Imran, Abdullah-Al-Zubaer; Terzopoulos, Demetri

doi:10.1109/icmla.2019.00137

Cited by 11 publications

(7 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They demonstrated that the combination of VAE and GAN provided significant improvements of semisupervised classification. Imran et al [25] used a network architecture that incorporates an ensemble of discriminators in a VAE-GAN network using datasets from the computer vision and medical imaging domains in order to generate new realistic images of medical data. They showed that the combination of this two generative models can lead to superior performances against state-of-the-art semi-supervised models both in image generation and classification tasks.…”

Section: Related Workmentioning

confidence: 99%

Data augmentation using generative adversarial neural networks on brain structural connectivity in multiple sclerosis

Barile

Marzullo

Stamile³

et al. 2021

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

Background and objective: Machine learning frameworks have demonstrated their potentials in dealing with complex data structures, achieving remarkable results in many areas, including brain imaging. However, a large collection of data is needed to train these models. This is particularly challenging in the biomedical domain since, due to acquisition accessibility, costs and pathology related variability, available datasets are limited and usually imbalanced. To overcome this challenge, generative models can be used to generate new data. Methods: In this study, a framework based on generative adversarial network is proposed to create synthetic structural brain networks in Multiple Sclerosis (MS). The dataset consists of 29 relapsingremitting and 19 secondary-progressive MS patients. T1 and diffusion tensor imaging (DTI) acquisitions were used to obtain the structural brain network for each subject. Evaluation of the quality of newly generated brain networks is performed by (i) analysing their structural properties and (ii) studying their impact on classification performance. Results: We demonstrate that advanced generative models could be directly applied to the structural brain networks. We quantitatively and qualitatively show that newly generated data do not present significant differences compared to the real ones. In addition, augmenting the existing dataset with generated samples leads to an improvement of the classification performance ( 1 81%) with respect to the baseline approach ( 1 66%). Conclusions: Our approach defines a new tool for biomedical application when connectome-based data augmentation is needed, providing a valid alternative to usual image-based data augmentation techniques.

show abstract

Section: Related Workmentioning

confidence: 99%

Data augmentation using generative adversarial neural networks on brain structural connectivity in multiple sclerosis

Barile

Marzullo

Stamile³

et al. 2021

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

show abstract

“…Adversarial learning has been utilized for segmentation (semantic-aware generative adversarial nets [4], structure correcting adversarial nets [5], etc.) as well as in disease classification from chest X-ray images (semi-supervised domain adaptation [6], attention-guided CNN [7], semi-supervised multi-adversarial encoder [8]).…”

Section: Related Workmentioning

confidence: 99%

Semi-supervised Multi-task Learning with Chest X-Ray Images

Imran

Terzopoulos

2019

Machine Learning in Medical Imaging

Self Cite

View full text Add to dashboard Cite

Discriminative models that require full supervision are inefficacious in the medical imaging domain when large labeled datasets are unavailable. By contrast, generative modeling-i.e., learning data generation and classification-facilitates semi-supervised training with limited labeled data. Moreover, generative modeling can be advantageous in accomplishing multiple objectives for better generalization. We propose a novel multi-task learning model for jointly learning a classifier and a segmentor, from chest X-ray images, through semi-supervised learning. In addition, we propose a new loss function that combines absolute KL divergence with Tversky loss (KLTV) to yield faster convergence and better segmentation performance. Based on our experimental results using a novel segmentation model, an Adversarial Pyramid Progressive Attention U-Net (APPAU-Net), we hypothesize that KLTV can be more effective for generalizing multi-tasking models while being competitive in segmentation-only tasks.

show abstract

“…In GANs, two neural networks, a generator and a discriminator, are trained together, where the generator attempts to generate images resembling real training samples while the discriminator distinguishes the generated samples from the generated ones. Many existing methods which use GANs for semi-supervised learning employ a single network for both classification and discrimination (Salimans et al 2016;Imran and Terzopoulos 2019). This means the network attempts to minimize two separate losses with the same parameters, which is our primary concern.…”

Section: Introductionmentioning

confidence: 99%

EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and GANs (Student Abstract)

Haque

2021

AAAI

View full text Add to dashboard Cite

Semi-supervised learning has been gaining attention as it allows for performing image analysis tasks such as classification with limited labeled data. Some popular algorithms using Generative Adversarial Networks (GANs) for semi-supervised classification share a single architecture for classification and discrimination. However, this may require a model to converge to a separate data distribution for each task, which may reduce overall performance. While progress in semi-supervised learning has been made, less addressed are small-scale, fully-supervised tasks where even unlabeled data is unavailable and unattainable. We therefore, propose a novel GAN model namely External Classifier GAN (EC-GAN), that utilizes GANs and semi-supervised algorithms to improve classification in fully-supervised regimes. Our method leverages a GAN to generate artificial data used to supplement supervised classification. More specifically, we attach an external classifier, hence the name EC-GAN, to the GAN’s generator, as opposed to sharing an architecture with the discriminator. Our experiments demonstrate that EC-GAN's performance is comparable to the shared architecture method, far superior to the standard data augmentation and regularization-based approach, and effective on a small, realistic dataset.

show abstract

Multi-adversarial Variational Autoencoder Networks

Cited by 11 publications

References 26 publications

Data augmentation using generative adversarial neural networks on brain structural connectivity in multiple sclerosis

Data augmentation using generative adversarial neural networks on brain structural connectivity in multiple sclerosis

Semi-supervised Multi-task Learning with Chest X-Ray Images

EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and GANs (Student Abstract)

Contact Info

Product

Resources

About