Object Detection using Domain Randomization and Generative Adversarial Refinement of Synthetic Images
This addresses the challenge of data scarcity in industrial settings, offering a solution for training object detectors with minimal real data, though it is incremental as it builds on existing domain randomization and GAN techniques.
The paper tackled the problem of training an object detector for industrial electric parts with limited real-world labeled data by using domain randomization and GANs to translate synthetic images to the real domain, achieving over 0.95 mean average precision in detection and classification.
In this work, we present an application of domain randomization and generative adversarial networks (GAN) to train a near real-time object detector for industrial electric parts, entirely in a simulated environment. Large scale availability of labelled real world data is typically rare and difficult to obtain in many industrial settings. As such here, only a few hundred of unlabelled real images are used to train a Cyclic-GAN network, in combination with various degree of domain randomization procedures. We demonstrate that this enables robust translation of synthetic images to the real world domain. We show that a combination of the original synthetic (simulation) and GAN translated images, when used for training a Mask-RCNN object detection network achieves greater than 0.95 mean average precision in detecting and classifying a collection of industrial electric parts. We evaluate the performance across different combinations of training data.