Generative One-Shot Learning (GOL): A Semi-Parametric Approach to One-Shot Learning in Autonomous Vision
This addresses the annotation bottleneck for autonomous driving systems, but appears incremental as it builds on existing one-shot learning methods.
The authors tackled the problem of reducing manual annotation for autonomous driving perception systems by proposing Generative One-Shot Learning (GOL), a semi-parametric approach that generates synthetic data from single one-shot objects, achieving evaluation on environment perception challenges.
Highly Autonomous Driving (HAD) systems rely on deep neural networks for the visual perception of the driving environment. Such networks are trained on large manually annotated databases. In this work, a semi-parametric approach to one-shot learning is proposed, with the aim of bypassing the manual annotation step required for training perceptions systems used in autonomous driving. The proposed generative framework, coined Generative One-Shot Learning (GOL), takes as input single one-shot objects, or generic patterns, and a small set of so-called regularization samples used to drive the generative process. New synthetic data is generated as Pareto optimal solutions from one-shot objects using a set of generalization functions built into a generalization generator. GOL has been evaluated on environment perception challenges encountered in autonomous vision.