Strategies for supplementing recurrent neural network training for spatio-temporal prediction
| Autor: | Stefan Elser, Markus Reischl, Ralf Mikut, Mark Schutera, Jochen Abhau |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Hyperparameter
0209 industrial biotechnology Computer science business.industry Generalization 02 engineering and technology Machine learning computer.software_genre Object (computer science) Automation Computer Science Applications Image (mathematics) 020901 industrial engineering & automation Recurrent neural network Control and Systems Engineering 0202 electrical engineering electronic engineering information engineering Trajectory 020201 artificial intelligence & image processing Artificial intelligence Electrical and Electronic Engineering business Generative adversarial network computer |
| Zdroj: | at - Automatisierungstechnik. 67:545-556 |
| ISSN: | 2196-677X 0178-2312 |
| Popis: | In autonomous driving, prediction tasks address complex spatio-temporal data. This article describes the examination of Recurrent Neural Networks (RNNs) for object trajectory prediction in the image space. The proposed methods enhance the performance and spatio-temporal prediction capabilities of Recurrent Neural Networks. Two different data augmentation strategies and a hyperparameter search are implemented for this purpose. A conventional data augmentation strategy and a Generative Adversarial Network (GAN) based strategy are analyzed with respect to their ability to close the generalization gap of Recurrent Neural Networks. The results are then discussed using single-object tracklets provided by the KITTI Tracking Dataset. This work demonstrates the benefits of augmenting spatio-temporal data with GANs. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|