Realistically distributing object placements in synthetic training data improves the performance of vision-based object detection models
2023-05-24Code Available0· sign in to hype
Setareh Dabiri, Vasileios Lioutas, Berend Zwartsenberg, Yunpeng Liu, Matthew Niedoba, Xiaoxuan Liang, Dylan Green, Justice Sefas, Jonathan Wilder Lavington, Frank Wood, Adam Scibior
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/inverted-ai/object-detectionOfficialIn papernone★ 0
Abstract
When training object detection models on synthetic data, it is important to make the distribution of synthetic data as close as possible to the distribution of real data. We investigate specifically the impact of object placement distribution, keeping all other aspects of synthetic data fixed. Our experiment, training a 3D vehicle detection model in CARLA and testing on KITTI, demonstrates a substantial improvement resulting from improving the object placement distribution.