TY - GEN
T1 - Attribute-controlled traffic data augmentation using conditional generative models
AU - Mukherjee, Amitangshu
AU - Joshi, Ameya
AU - Sarkar, Soumik
AU - Hegde, Chinmay
N1 - Funding Information:
∗This work was supported in part by NSF grants CCF-1750920, CNS-1845969, DARPA AIRA grant PA-18-02-02, AFOSR YIP Grant FA9550-17-1-0220, an ERP grant from Iowa State University, a GPU gift grant from NVIDIA corporation, and faculty fellowships from the Black and Veatch Foundation.
Publisher Copyright:
© 2019 IEEE Computer Society. All rights reserved.
PY - 2019/6
Y1 - 2019/6
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85099447878&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85099447878&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85099447878
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 83
EP - 87
BT - Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
PB - IEEE Computer Society
T2 - 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
Y2 - 16 June 2019 through 20 June 2019
ER -