Search Results for author: Diane Oyen

Found 15 papers, 1 papers with code

On visual self-supervision and its effect on model robustness

no code implementations8 Dec 2021 Michal Kucer, Diane Oyen, Garrett Kenyon

We identify primary ways in which self-supervision can be added to adversarial training, and observe that using a self-supervised loss to optimize both network parameters and find adversarial examples leads to the strongest improvement in model robustness, as this can be viewed as a form of ensemble adversarial training.

Out-of-Distribution Detection Self-Supervised Learning

Learning to Pre-process Laser Induced Breakdown Spectroscopy Signals Without Clean Data

no code implementations26 Oct 2021 Juan Castorena, Diane Oyen

This work tests whether deep neural networks can clean laser induced breakdown spectroscopy (LIBS) signals by using only uncleaned raw measurements.


Transfer learning with fewer ImageNet classes

no code implementations NeurIPS Workshop ImageNet_PPF 2021 Michal Kucer, Diane Oyen

Though much previous work tried to uncover the best practices for transfer learning, much is left unexplored.

Transfer Learning

Diff2Dist: Learning Spectrally Distinct Edge Functions, with Applications to Cell Morphology Analysis

no code implementations29 Jun 2021 Cory Braker Scott, Eric Mjolsness, Diane Oyen, Chie Kodera, David Bouchez, Magalie Uyttewaal

Because all steps involved in calculating this modified GDD are differentiable, we demonstrate that it is possible for a small neural network model to learn edge weights which minimize loss.

Deep Spectral CNN for Laser Induced Breakdown Spectroscopy

no code implementations3 Dec 2020 Juan Castorena, Diane Oyen, Ann Ollila, Carey Legget, Nina Lanza

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 the sources of sensor uncertainty (i. e., pre-process) and (2) get qualitative and quantitative measures of chemical content of a sample given a spectral signal (i. e., calibrate).

StressNet: Deep Learning to Predict Stress With Fracture Propagation in Brittle Materials

no code implementations20 Nov 2020 Yinan Wang, Diane Oyen, Weihong, Guo, Anishi Mehta, Cory Braker Scott, Nishant Panda, M. Giselle Fernández-Godino, Gowri Srinivasan, Xiaowei Yue

Catastrophic failure in brittle materials is often due to the rapid growth and coalescence of cracks aided by high internal stresses.

Diagram Image Retrieval using Sketch-Based Deep Learning and Transfer Learning

no code implementations22 Apr 2020 Manish Bhattarai, Diane Oyen, Juan Castorena, Liping Yang, Brendt Wohlberg

We then use our small set of manually labeled patent diagram images via transfer learning to adapt the image search from sketches of natural images to diagrams.

Image Classification Image Retrieval +2

Learning Spatial Relationships between Samples of Patent Image Shapes

no code implementations12 Apr 2020 Juan Castorena, Manish Bhattarai, Diane Oyen

Binary image based classification and retrieval of documents of an intellectual nature is a very challenging problem.

General Classification Image Generation

TGGLines: A Robust Topological Graph Guided Line Segment Detector for Low Quality Binary Images

no code implementations27 Feb 2020 Ming Gong, Liping Yang, Catherine Potts, Vijayan K. Asari, Diane Oyen, Brendt Wohlberg

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 detection for autonomous driving.

Autonomous Driving Line Detection +1

Learning Planar Ising Models

no code implementations3 Feb 2015 Jason K. Johnson, Diane Oyen, Michael Chertkov, Praneeth Netrapalli

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.

Bayesian Discovery of Multiple Bayesian Networks via Transfer Learning

no code implementations9 Jul 2013 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 that produce observed data.

Transfer Learning

Controlling the Precision-Recall Tradeoff in Differential Dependency Network Analysis

no code implementations9 Jul 2013 Diane Oyen, Alexandru Niculescu-Mizil, Rachel Ostroff, Alex Stewart, Vincent P. Clark

We then show that by imposing a bias towards learning similar dependency networks for each condition the false discovery rates can be reduced to acceptable levels, at the cost of finding a reduced number of differences.

Transfer Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.