no code implementations • 1 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.
1 code implementation • 18 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.
no code implementations • 9 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.
1 code implementation • 9 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.
no code implementations • 9 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.
1 code implementation • 16 Apr 2020 • Aryan Mobiny, Pietro Antonio Cicalese, Samira Zare, Pengyu Yuan, Mohammadsajad Abavisani, Carol C. Wu, Jitesh Ahuja, Patricia M. de Groot, Hien Van Nguyen
The network then uses the activation maps to focus on regions of interest and combines both coarse and fine-grained representations of the data.
no code implementations • 4 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.
3 code implementations • 7 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.
1 code implementation • 19 Jun 2018 • Aryan Mobiny, Hien Van Nguyen
We show that CapsNets significantly outperforms CNNs when the number of training samples is small.
no code implementations • 2 May 2018 • Aryan Mobiny, Mohammad Najarian
For speaker verification, at first, a background model must be created for speaker representation.
no code implementations • 11 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.