Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data

10/23/2018
by   Aayush Prakash, et al.
0

We present structured domain randomization (SDR), a variant of domain randomization (DR) that takes into account the structure and context of the scene. In contrast to DR, which places objects and distractors randomly according to a uniform probability distribution, SDR places objects and distractors randomly according to probability distributions that arise from the specific problem at hand. In this manner, SDR-generated imagery enables the neural network to take the context around an object into consideration during detection. We demonstrate the power of SDR for the problem of 2D bounding box car detection, achieving competitive results on real data after training only on synthetic data. On the KITTI easy, moderate, and hard tasks, we show that SDR outperforms other approaches to generating synthetic data (VKITTI, Sim 200k, or DR), as well as real data collected in a different domain (BDD100K). Moreover, synthetic SDR data combined with real KITTI data outperforms real KITTI data alone.

READ FULL TEXT

page 3

page 5

page 6

research
04/18/2018

Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization

We present a system for training deep neural networks for object detecti...
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
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
05/24/2023

Realistically distributing object placements in synthetic training data improves the performance of vision-based object detection models

When training object detection models on synthetic data, it is important...
research
05/23/2019

Watermark retrieval from 3D printed objects via synthetic data training

We present a deep neural network based method for the retrieval of water...
research
11/11/2021

Training neural networks with synthetic electrocardiograms

We present a method for training neural networks with synthetic electroc...
research
05/13/2022

Virtual passengers for real car solutions: synthetic datasets

Strategies that include the generation of synthetic data are beginning t...

Please sign up or login with your details

Forgot password? Click here to reset