DeepAI AI Chat
Log In Sign Up

VADRA: Visual Adversarial Domain Randomization and Augmentation

by   Rawal Khirodkar, et al.
Carnegie Mellon University

We address the issue of learning from synthetic domain randomized data effectively. While previous works have showcased domain randomization as an effective learning approach, it lacks in challenging the learner and wastes valuable compute on generating easy examples. This can be attributed to uniform randomization over the rendering parameter distribution. In this work, firstly we provide a theoretical perspective on characteristics of domain randomization and analyze its limitations. As a solution to these limitations, we propose a novel algorithm which closes the loop between the synthetic generative model and the learner in an adversarial fashion. Our framework easily extends to the scenario when there is unlabelled target data available, thus incorporating domain adaptation. We evaluate our method on diverse vision tasks using state-of-the-art simulators for public datasets like CLEVR, Syn2Real, and VIRAT, where we demonstrate that a learner trained using adversarial data generation performs better than using a random data generation strategy.


page 1

page 5

page 6

page 7

page 8


Domain Randomization for Scene-Specific Car Detection and Pose Estimation

We address the issue of domain gap when making use of synthetic data to ...

Active Domain Randomization

Domain randomization is a popular technique for improving domain transfe...

Domain Adaptation: the Key Enabler of Neural Network Equalizers in Coherent Optical Systems

We introduce the domain adaptation and randomization approach for calibr...

Unity Perception: Generate Synthetic Data for Computer Vision

We introduce the Unity Perception package which aims to simplify and acc...

DeceptionNet: Network-Driven Domain Randomization

We present a novel approach to tackle domain adaptation between syntheti...