Evaluating generative networks using Gaussian mixtures of image features

no code implementations • 8 Oct 2021 • Lorenzo Luzi, Carlos Ortiz Marrero, Nile Wynar, Richard G. Baraniuk, Michael J. Henry

We define a performance measure, which we call WaM, on two sets of images by using Inception-v3 (or another classifier) to featurize the images, estimate two GMMs, and use the restricted $2$-Wasserstein distance to compare the GMMs.

The Outer Product Structure of Neural Network Derivatives

no code implementations • 9 Oct 2018 • Craig Bakker, Michael J. Henry, Nathan O. Hodas

In this paper, we show that feedforward and recurrent neural networks exhibit an outer product derivative structure but that convolutional neural networks do not.

Understanding and Exploiting the Low-Rank Structure of Deep Networks

no code implementations • ICLR 2018 • Craig Bakker, Michael J. Henry, Nathan O. Hodas

Training methods for deep networks are primarily variants on stochastic gradient descent.

Multi-modal Geolocation Estimation Using Deep Neural Networks

no code implementations • 26 Dec 2017 • Jesse M. Johns, Jeremiah Rounds, Michael J. Henry

Estimating the location where an image was taken based solely on the contents of the image is a challenging task, even for humans, as properly labeling an image in such a fashion relies heavily on contextual information, and is not as simple as identifying a single object in the image.