research
∙
10/10/2022
A Memory Transformer Network for Incremental Learning
We study class-incremental learning, a training setup in which new class...
share
research
∙
04/26/2021
3D Scene Compression through Entropy Penalized Neural Representation Functions
Some forms of novel visual media enable the viewer to explore a 3D scene...
research
∙
10/26/2020
Reducing the Computational Cost of Deep Generative Models with Binary Neural Networks
Deep generative models provide a powerful set of tools to understand rea...
research
∙
12/20/2019
HiLLoC: Lossless Image Compression with Hierarchical Latent Variable Models
We make the following striking observation: fully convolutional VAE mode...
research
∙
07/27/2019
Variational f-divergence Minimization
Probabilistic models are often trained by maximum likelihood, which corr...
research
∙
11/21/2018
Spread Divergences
For distributions p and q with different support, the divergence general...
research
∙
09/13/2018