MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction
Abstract
Pedestrian trajectory prediction is challenging due to its uncertain and multimodal nature. While generative adversarial networks can learn a distribution over future trajectories, they tend to predict out-of-distribution samples when the distribution of future trajectories is a mixture of multiple, possibly disconnected modes. To address this issue, we propose a multi-generator model for pedestrian trajectory prediction. Each generator specializes in learning a distribution over trajectories routing towards one of the primary modes in the scene, while a second network learns a categorical distribution over these generators, conditioned on the dynamics and scene input. This architecture allows us to effectively sample from specialized generators and to significantly reduce the out-of-distribution samples compared to single generator methods.
Cite
Text
Dendorfer et al. "MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction." International Conference on Computer Vision, 2021. doi:10.1109/ICCV48922.2021.01291Markdown
[Dendorfer et al. "MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction." International Conference on Computer Vision, 2021.](https://mlanthology.org/iccv/2021/dendorfer2021iccv-mggan/) doi:10.1109/ICCV48922.2021.01291BibTeX
@inproceedings{dendorfer2021iccv-mggan,
title = {{MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction}},
author = {Dendorfer, Patrick and Elflein, Sven and Leal-Taixé, Laura},
booktitle = {International Conference on Computer Vision},
year = {2021},
pages = {13158-13167},
doi = {10.1109/ICCV48922.2021.01291},
url = {https://mlanthology.org/iccv/2021/dendorfer2021iccv-mggan/}
}