136 citations · 219 across the 18 of their papers we have counts for
20 papers
Discovering Image Usage Online: A Case Study With "Flatten the Curve''
Shawn M. Jones, Diane Oyen
Understanding the spread of images across the web helps us understand the reuse of scientific visualizations and their relationship with the public. The "Flatten the Curve" graphic…
Semi-supervised Learning of Pushforwards For Domain Translation & Adaptation
Nishant Panda, Natalie Klein, Dominic Yang +2
Given two probability densities on related data spaces, we seek a map pushing one density to the other while satisfying application-dependent constraints. For maps to have utility…
Generative structured normalizing flow Gaussian processes applied to spectroscopic data
Natalie Klein, Nishant Panda, Patrick Gasda +1
In this work, we propose a novel generative model for mapping inputs to structured, high-dimensional outputs using structured conditional normalizing flows and Gaussian process reg…
Abstract Images Have Different Levels of Retrievability Per Reverse Image Search Engine
Shawn M. Jones, Diane Oyen
Much computer vision research has focused on natural images, but technical documents typically consist of abstract images, such as charts, drawings, diagrams, and schematics. How w…
Robustness to Label Noise Depends on the Shape of the Noise Distribution in Feature Space
Diane Oyen, Michal Kucer, Nick Hengartner +1
Machine learning classifiers have been demonstrated, both empirically and theoretically, to be robust to label noise under certain conditions -- notably the typical assumption is t…
On visual self-supervision and its effect on model robustness
Michal Kucer, Diane Oyen, Garrett Kenyon
Recent self-supervision methods have found success in learning feature representations that could rival ones from full supervision, and have been shown to be beneficial to the mode…
SpectroscopyNet: Learning to pre-process Spectroscopy Signals without clean data
Juan Castorena, Diane Oyen
In this work we propose a deep learning approach to clean spectroscopy signals using only uncleaned data. Cleaning signals from spectroscopy instrument noise is challenging as nois…
Neural density estimation and uncertainty quantification for laser induced breakdown spectroscopy spectra
Katiana Kontolati, Natalie Klein, Nishant Panda +1
Constructing probability densities for inference in high-dimensional spectral data is often intractable. In this work, we use normalizing flows on structured spectral latent spaces…
Diff2Dist: Learning Spectrally Distinct Edge Functions, with Applications to Cell Morphology Analysis
Cory Braker Scott, Eric Mjolsness, Diane Oyen +3
We present a method for learning "spectrally descriptive" edge weights for graphs. We generalize a previously known distance measure on graphs (Graph Diffusion Distance), thereby a…
Deep Spectral CNN for Laser Induced Breakdown Spectroscopy
Juan Castorena, Diane Oyen, Ann Ollila +2
This work proposes a spectral convolutional neural network (CNN) operating on laser induced breakdown spectroscopy (LIBS) signals to learn to (1) disentangle spectral signals from…
StressNet: Deep Learning to Predict Stress With Fracture Propagation in Brittle Materials
Yinan Wang, Diane Oyen, Weihong +7
Catastrophic failure in brittle materials is often due to the rapid growth and coalescence of cracks aided by high internal stresses. Hence, accurate prediction of maximum internal…
Learning Spatial Relationships between Samples of Patent Image Shapes
Juan Castorena, Manish Bhattarai, Diane Oyen
Binary image based classification and retrieval of documents of an intellectual nature is a very challenging problem. Variations in the binary image generation mechanisms which are…
Diagram Image Retrieval using Sketch-Based Deep Learning and Transfer Learning
Manish Bhattarai, Diane Oyen, Juan Castorena +2
Resolution of the complex problem of image retrieval for diagram images has yet to be reached. Deep learning methods continue to excel in the fields of object detection and image c…
TGGLines: A Robust Topological Graph Guided Line Segment Detector for Low Quality Binary Images
Ming Gong, Liping Yang, Catherine Potts +3
Line segment detection is an essential task in computer vision and image analysis, as it is the critical foundation for advanced tasks such as shape modeling and road lane line det…
The ISTI Rapid Response on Exploring Cloud Computing 2018
Carleton Coffrin, James Arnold, Stephan Eidenbenz +45
This report describes eighteen projects that explored how commercial cloud computing services can be utilized for scientific computation at national laboratories. These demonstrati…
Quantum Algorithm Implementations for Beginners
Abhijith J., Adetokunbo Adedoyin, John Ambrosiano +31
As quantum computers become available to the general public, the need has arisen to train a cohort of quantum programmers, many of whom have been developing classical computer prog…
Learning Planar Ising Models
Jason K. Johnson, Diane Oyen, Michael Chertkov +1
Inference and learning of graphical models are both well-studied problems in statistics and machine learning that have found many applications in science and engineering. However,…
Controlling the Precision-Recall Tradeoff in Differential Dependency Network Analysis
Diane Oyen, Alexandru Niculescu-Mizil, Rachel Ostroff +2
Graphical models have gained a lot of attention recently as a tool for learning and representing dependencies among variables in multivariate data. Often, domain scientists are loo…
Bayesian Discovery of Multiple Bayesian Networks via Transfer Learning
Diane Oyen, Terran Lane
Bayesian network structure learning algorithms with limited data are being used in domains such as systems biology and neuroscience to gain insight into the underlying processes th…
Learning Planar Ising Models
Jason K. Johnson, Praneeth Netrapalli, Michael Chertkov
Inference and learning of graphical models are both well-studied problems in statistics and machine learning that have found many applications in science and engineering. However,…