activity
20182021
most citedRadiologist-Level COVID-19 Detection Using CT Scans with Detail-Oriented Capsule Networks

73 citations · 127 across the 8 of their papers we have counts for

collaborators

11 papers

eess.IV20212 cited

Multimodal Breast Lesion Classification Using Cross-Attention Deep Networks

Hung Q. Vo, Pengyu Yuan, Tiancheng He +2

Accurate breast lesion risk estimation can significantly reduce unnecessary biopsies and help doctors decide optimal treatment plans. Most existing computer-aided systems rely sole…

cs.CV2021

PICASO: Permutation-Invariant Cascaded Attentional Set Operator

Samira Zare, Hien Van Nguyen

Set-input deep networks have recently drawn much interest in computer vision and machine learning. This is in part due to the increasing number of important tasks such as meta-lear…

eess.IV202120 cited

First arrival picking using U-net with Lovasz loss and nearest point picking method

Pengyu Yuan, Wenyi Hu, Xuqing Wu +2

We proposed a robust segmentation and picking workflow to solve the first arrival picking problem for seismic signal processing. Unlike traditional classification algorithm, image…

cs.LG202018 cited

Evaluation of Inference Attack Models for Deep Learning on Medical Data

Maoqiang Wu, Xinyue Zhang, Jiahao Ding +4

Deep learning has attracted broad interest in healthcare and medical communities. However, there has been little research into the privacy issues created by deep networks trained f…

cs.CV2020

DECAPS: Detail-Oriented Capsule Networks

Aryan Mobiny, Pengyu Yuan, Pietro Antonio Cicalese +1

Capsule Networks (CapsNets) have demonstrated to be a promising alternative to Convolutional Neural Networks (CNNs). However, they often fall short of state-of-the-art accuracies o…

cs.CV20203 cited

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

Pengyu Yuan, Aryan Mobiny, Jahandar Jahanipour +6

Deep Neural Networks (or DNNs) must constantly cope with distribution changes in the input data when the task of interest or the data collection protocol changes. Retraining a netw…