A Contrastive Learning Approach to Auroral Identification and Classification

no code implementations • 28 Sep 2021 • Jeremiah W. Johnson, Swathi Hari, Donald Hampton, Hyunju K. Connor, Amy Keesee

Unsupervised learning algorithms are beginning to achieve accuracies comparable to their supervised counterparts on benchmark computer vision tasks, but their utility for practical applications has not yet been demonstrated.

Classification Contrastive Learning +1

Detecting Invasive Ductal Carcinoma with Semi-Supervised Conditional GANs

no code implementations • 14 Nov 2019 • Jeremiah W. Johnson

Invasive ductal carcinoma (IDC) comprises nearly 80% of all breast cancers.

Predicting Patient Outcomes

Structured Prediction using cGANs with Fusion Discriminator

no code implementations • ICLR 2019 • Faisal Mahmood, Wenhao Xu, Nicholas J. Durr, Jeremiah W. Johnson, Alan Yuille

We propose the fusion discriminator, a single unified framework for incorporating conditional information into a generative adversarial network (GAN) for a variety of distinct structured prediction tasks, including image synthesis, semantic segmentation, and depth estimation.

Depth Estimation Generative Adversarial Network +3

Adapting Mask-RCNN for Automatic Nucleus Segmentation

no code implementations • 1 May 2018 • Jeremiah W. Johnson

Automatic segmentation of microscopy images is an important task in medical image processing and analysis.

Instance Segmentation Object +5