VADRA: Visual Adversarial Domain Randomization and Augmentation

12/03/2018
by   Rawal Khirodkar, et al.
0

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.

READ FULL TEXT

page 1

page 5

page 6

page 7

page 8

research
11/14/2018

Domain Randomization for Scene-Specific Car Detection and Pose Estimation

We address the issue of domain gap when making use of synthetic data to ...
research
04/09/2019

Active Domain Randomization

Domain randomization is a popular technique for improving domain transfe...
research
02/25/2022

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

We introduce the domain adaptation and randomization approach for calibr...
research
07/09/2021

Unity Perception: Generate Synthetic Data for Computer Vision

We introduce the Unity Perception package which aims to simplify and acc...
research
04/04/2019

DeceptionNet: Network-Driven Domain Randomization

We present a novel approach to tackle domain adaptation between syntheti...
research
09/23/2022

Comparison of synthetic dataset generation methods for medical intervention rooms using medical clothing detection as an example

The availability of real data from areas with high privacy requirements,...
research
06/15/2022

Robust SAR ATR on MSTAR with Deep Learning Models trained on Full Synthetic MOCEM data

The promising potential of Deep Learning for Automatic Target Recognitio...

Please sign up or login with your details

Forgot password? Click here to reset