Search Results for author:
Found 2 papers, 2 papers with code
Do Deep Networks Transfer Invariances Across Classes?
Based on this analysis, we show how a generative approach for learning the nuisance transformations can help transfer invariances across classes and improve performance on a set of imbalanced image classification benchmarks.
Ranked #21 on
Long-tail Learning
on CIFAR-10-LT (ρ=100)
Meta-Learning Symmetries by Reparameterization
We present a method for learning and encoding equivariances into networks by learning corresponding parameter sharing patterns from data.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
