Search Results for author:
Found 6 papers, 4 papers with code
A Mutual Information Perspective on Federated Contrastive Learning
Along with the proposed SimCLR extensions, we also study how different sources of non-i. i. d.-ness can impact the performance of federated unsupervised learning through global mutual information maximization; we find that a global objective is beneficial for some sources of non-i. i. d.-ness but can be detrimental for others.
Self-improving Multiplane-to-layer Images for Novel View Synthesis
We present a new method for lightweight novel-view synthesis that generalizes to an arbitrary forward-facing scene.
Stereo Magnification with Multi-Layer Images
The second stage infers the color and the transparency values for these layers producing the final representation for novel view synthesis.
Ranked #1 on
Novel View Synthesis
on SWORD
Image Generators with Conditionally-Independent Pixel Synthesis
Existing image generator networks rely heavily on spatial convolutions and, optionally, self-attention blocks in order to gradually synthesize images in a coarse-to-fine manner.
Ranked #1 on
Image Generation
on Satellite-Landscapes 256 x 256
High-Resolution Daytime Translation Without Domain Labels
We present the high-resolution daytime translation (HiDT) model for this task.
YASENN: Explaining Neural Networks via Partitioning Activation Sequences
We introduce a novel approach to feed-forward neural network interpretation based on partitioning the space of sequences of neuron activations.
