Search Results for author:
Found 10 papers, 2 papers with code
Adversarial Attacks with Time-Scale Representations
Third, we generate new adversarial images by projecting back the original coefficients from the low scale and the perturbed coefficients from the high scale sub-space.
Symbolic Semantic Segmentation and Interpretation of COVID-19 Lung Infections in Chest CT volumes based on Emergent Languages
We show state of the art results for segmentation of COVID-19 lung infections in CT.
Emergent symbolic language based deep medical image classification
In this work, we demonstrate for the first time, the emer-gence of deep symbolic representations of emergent language in the frame-work of image classification.
Image-driven discriminative and generative machine learning algorithms for establishing microstructure-processing relationships
A binary alloy (uranium-molybdenum) that is currently under development as a nuclear fuel was studied for the purpose of developing an improved machine learning approach to image recognition, characterization, and building predictive capabilities linking microstructure to processing conditions.
Automated Phenotyping via Cell Auto Training (CAT) on the Cell DIVE Platform
We present a method for automatic cell classification in tissue samples using an automated training set from multiplexed immunofluorescence images.
Towards Emergent Language Symbolic Semantic Segmentation and Model Interpretability
A UNet-like architecture is used to generate input to the Sender network which produces a symbolic sentence, and a Receiver network co-generates the segmentation mask based on the sentence.
ESCELL: Emergent Symbolic Cellular Language
In one form of the game, a sender and a receiver observe a set of cells from 5 different cell phenotypes.
FastEstimator: A Deep Learning Library for Fast Prototyping and Productization
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 practitioners around the world.
Quantifying error contributions of computational steps, algorithms and hyperparameter choices in image classification pipelines
We show that algorithm selection and hyper-parameter optimization methods can be used to quantify the error contribution and that random search is able to quantify the contribution more accurately than Bayesian optimization.
Quantifying contribution and propagation of error from computational steps, algorithms and hyperparameter choices in image classification pipelines
The agnostic and naive methodologies quantify the error contribution and propagation respectively from the computational steps, algorithms and hyperparameters in the image classification pipeline.
