5 citations · 5 across the 1 of their papers we have counts for
3 papers
Canonical Face Embeddings
David McNeely-White, Ben Sattelberg, Nathaniel Blanchard +1
We present evidence that many common convolutional neural networks (CNNs) trained for face verification learn functions that are nearly equivalent under rotation. More specifically…
Locally Linear Attributes of ReLU Neural Networks
Ben Sattelberg, Renzo Cavalieri, Michael Kirby +2
A ReLU neural network determines/is a continuous piecewise linear map from an input space to an output space. The weights in the neural network determine a decomposition of the inp…
Exploring the Interchangeability of CNN Embedding Spaces
David McNeely-White, Benjamin Sattelberg, Nathaniel Blanchard +1
CNN feature spaces can be linearly mapped and consequently are often interchangeable. This equivalence holds across variations in architectures, training datasets, and network task…