50 citations · 77 across the 10 of their papers we have counts for
6 papers · 1 filter
Adversarial Attacks with Time-Scale Representations
Alberto Santamaria-Pang, Jianwei Qiu, Aritra Chowdhury +4
We propose a novel framework for real-time black-box universal attacks which disrupts activations of early convolutional layers in deep learning models. Our hypothesis is that pert…
Symbolic Semantic Segmentation and Interpretation of COVID-19 Lung Infections in Chest CT volumes based on Emergent Languages
Aritra Chowdhury, Alberto Santamaria-Pang, James R. Kubricht +2
The coronavirus disease (COVID-19) has resulted in a pandemic crippling the a breadth of services critical to daily life. Segmentation of lung infections in computerized tomography…
Emergent symbolic language based deep medical image classification
Aritra Chowdhury, Alberto Santamaria-Pang, James R. Kubricht +1
Modern deep learning systems for medical image classification have demonstrated exceptional capabilities for distinguishing between image based medical categories. However, they ar…
FastEstimator: A Deep Learning Library for Fast Prototyping and Productization
Xiaomeng Dong, Junpyo Hong, Hsi-Ming Chang +10
As the complexity of state-of-the-art deep learning models increases by the month, implementation, interpretation, and traceability become ever-more-burdensome challenges for AI pr…
Quantifying error contributions of computational steps, algorithms and hyperparameter choices in image classification pipelines
Aritra Chowdhury, Malik Magdin-Ismail, Bulent Yener
Data science relies on pipelines that are organized in the form of interdependent computational steps. Each step consists of various candidate algorithms that maybe used for perfor…
Quantifying contribution and propagation of error from computational steps, algorithms and hyperparameter choices in image classification pipelines
Aritra Chowdhury, Malik Magdon-Ismail, Bulent Yener
Data science relies on pipelines that are organized in the form of interdependent computational steps. Each step consists of various candidate algorithms that maybe used for perfor…