Search Results for author: Aryan Mobiny

Found 11 papers, 5 papers with code

Trans-Caps: Transformer Capsule Networks with Self-attention Routing

no code implementations1 Jan 2021 Aryan Mobiny, Pietro Antonio Cicalese, Hien Van Nguyen

Capsule Networks (CapsNets) have shown to be a promising alternative to Convolutional Neural Networks (CNNs) in many computer vision tasks, due to their ability to encode object viewpoint variations.

Kidney Level Lupus Nephritis Classification using Uncertainty Guided Bayesian Convolutional Neural Networks

1 code implementation18 Nov 2020 Pietro A. Cicalese, Aryan Mobiny, Zahed Shahmoradi, Xiongfeng Yi, Chandra Mohan, Hien Van Nguyen

The kidney biopsy based diagnosis of Lupus Nephritis (LN) is characterized by low inter-observer agreement, with misdiagnosis being associated with increased patient morbidity and mortality.

Classification General Classification

Few Is Enough: Task-Augmented Active Meta-Learning for Brain Cell Classification

no code implementations9 Jul 2020 Pengyu Yuan, Aryan Mobiny, Jahandar Jahanipour, Xiaoyang Li, Pietro Antonio Cicalese, Badrinath Roysam, Vishal Patel, Maric Dragan, Hien Van Nguyen

Meta-learning aims to deliver an adaptive model that is sensitive to these underlying distribution changes, but requires many tasks during the meta-training process.

Active Learning General Classification +1

DECAPS: Detail-Oriented Capsule Networks

no code implementations9 Jul 2020 Aryan Mobiny, Pengyu Yuan, Pietro Antonio Cicalese, Hien Van Nguyen

We provide extensive experiments on the CheXpert and RSNA Pneumonia datasets to validate the effectiveness of DECAPS.

Pneumonia Detection

StyPath: Style-Transfer Data Augmentation For Robust Histology Image Classification

1 code implementation9 Jul 2020 Pietro Antonio Cicalese, Aryan Mobiny, Pengyu Yuan, Jan Becker, Chandra Mohan, Hien Van Nguyen

We also generated Grad-CAM representations of the results which were assessed by an experienced nephropathologist; we used this qualitative analysis to elucidate on the assumptions being made by each model.

Classification Data Augmentation +3

DVNet: A Memory-Efficient Three-Dimensional CNN for Large-Scale Neurovascular Reconstruction

no code implementations4 Feb 2020 Leila Saadatifard, Aryan Mobiny, Pavel Govyadinov, Hien Nguyen, David Mayerich

Maps of brain microarchitecture are important for understanding neurological function and behavior, including alterations caused by chronic conditions such as neurodegenerative disease.

Semantic Segmentation

DropConnect Is Effective in Modeling Uncertainty of Bayesian Deep Networks

3 code implementations7 Jun 2019 Aryan Mobiny, Hien V. Nguyen, Supratik Moulik, Naveen Garg, Carol C. Wu

In this paper, we develop a theoretical framework to approximate Bayesian inference for DNNs by imposing a Bernoulli distribution on the model weights.

Autonomous Driving Bayesian Inference +2

Fast CapsNet for Lung Cancer Screening

1 code implementation19 Jun 2018 Aryan Mobiny, Hien Van Nguyen

We show that CapsNets significantly outperforms CNNs when the number of training samples is small.

Computed Tomography (CT) General Classification +2

Text-Independent Speaker Verification Using Long Short-Term Memory Networks

no code implementations2 May 2018 Aryan Mobiny, Mohammad Najarian

For speaker verification, at first, a background model must be created for speaker representation.

Text-Independent Speaker Verification

Lung Cancer Screening Using Adaptive Memory-Augmented Recurrent Networks

no code implementations11 Oct 2017 Aryan Mobiny, Supratik Moulik, Hien Van Nguyen

In this paper, we investigate the effectiveness of deep learning techniques for lung nodule classification in computed tomography scans.

Classification General Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.