130 citations · 135 across the 3 of their papers we have counts for
3 papers
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…
Using Simulated Data to Generate Images of Climate Change
Gautier Cosne, Adrien Juraver, Mélisande Teng +4
Generative adversarial networks (GANs) used in domain adaptation tasks have the ability to generate images that are both realistic and personalized, transforming an input image whi…
Quantifying the Carbon Emissions of Machine Learning
Alexandre Lacoste, Alexandra Luccioni, Victor Schmidt +1
From an environmental standpoint, there are a few crucial aspects of training a neural network that have a major impact on the quantity of carbon that it emits. These factors inclu…