Attribute-Controlled Traffic Data Augmentation Using Conditional Generative Models
Abstract
Perception systems of self-driving vehicles require large amounts of diverse data to be robust against adverse lighting and weather conditions. Collection and annotation of such traffic data is resource-intensive and expensive. To circumvent this challenge, we introduce an approach where we train attribute-based generative models conditioned on the time-of-day labels to reconstruct semantically valid transformed versions of the original data. We further show the generalization capabilities of our model where they are able to reconstruct full traffic scenes despite having only being trained on constrained crops of the original images. Finally, we present a new dataset derived from an original traffic scene dataset augmented with data generated by our attribute-based conditional generative models.
Cite
Text
Mukherjee et al. "Attribute-Controlled Traffic Data Augmentation Using Conditional Generative Models." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.Markdown
[Mukherjee et al. "Attribute-Controlled Traffic Data Augmentation Using Conditional Generative Models." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/mukherjee2019cvprw-attributecontrolled/)BibTeX
@inproceedings{mukherjee2019cvprw-attributecontrolled,
title = {{Attribute-Controlled Traffic Data Augmentation Using Conditional Generative Models}},
author = {Mukherjee, Amitangshu and Joshi, Ameya and Sarkar, Soumik and Hegde, Chinmay},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2019},
pages = {83-87},
url = {https://mlanthology.org/cvprw/2019/mukherjee2019cvprw-attributecontrolled/}
}