4 citations · 8 across the 10 of their papers we have counts for
4 papers · 1 filter
Towards Composable Distributions of Latent Space Augmentations
Omead Pooladzandi, Jeffrey Jiang, Sunay Bhat +1
We propose a composable framework for latent space image augmentation that allows for easy combination of multiple augmentations. Image augmentation has been shown to be an effecti…
Causal Structural Hypothesis Testing and Data Generation Models
Jeffrey Jiang, Omead Pooladzandi, Sunay Bhat +1
A vast amount of expert and domain knowledge is captured by causal structural priors, yet there has been little research on testing such priors for generalization and data synthesi…
De-Biasing Generative Models using Counterfactual Methods
Sunay Bhat, Jeffrey Jiang, Omead Pooladzandi +1
Variational autoencoders (VAEs) and other generative methods have garnered growing interest not just for their generative properties but also for the ability to dis-entangle a low-…
tsBNgen: A Python Library to Generate Time Series Data from an Arbitrary Dynamic Bayesian Network Structure
Manie Tadayon, Greg Pottie
Synthetic data is widely used in various domains. This is because many modern algorithms require lots of data for efficient training, and data collection and labeling usually are a…