activity
20182020
collaborators

7 papers

cs.CV2020

Image-to-image Mapping with Many Domains by Sparse Attribute Transfer

Matthew Amodio, Rim Assouel, Victor Schmidt +3

Unsupervised image-to-image translation consists of learning a pair of mappings between two domains without known pairwise correspondences between points. The current convention is…

cs.CV2019

TraVeLGAN: Image-to-image Translation by Transformation Vector Learning

Matthew Amodio, Smita Krishnaswamy

Interest in image-to-image translation has grown substantially in recent years with the success of unsupervised models based on the cycle-consistency assumption. The achievements o…

cs.LG2019

Generating and Aligning from Data Geometries with Generative Adversarial Networks

Matthew Amodio, Smita Krishnaswamy

Unsupervised domain mapping has attracted substantial attention in recent years due to the success of models based on the cycle-consistency assumption. These models map between two…

cs.LG2019

Finding Archetypal Spaces Using Neural Networks

David van Dijk, Daniel Burkhardt, Matthew Amodio +3

Archetypal analysis is a data decomposition method that describes each observation in a dataset as a convex combination of "pure types" or archetypes. These archetypes represent ex…

cs.LG2018

Interpretable Neuron Structuring with Graph Spectral Regularization

Alexander Tong, David van Dijk, Jay S. Stanley +6

While neural networks are powerful approximators used to classify or embed data into lower dimensional spaces, they are often regarded as black boxes with uninterpretable features.…

q-bio.QM2018

Out-of-Sample Extrapolation with Neuron Editing

Matthew Amodio, David van Dijk, Ruth Montgomery +2

While neural networks can be trained to map from one specific dataset to another, they usually do not learn a generalized transformation that can extrapolate accurately outside the…