Khan Q, Wenzel P, Cremers D, Leal-Taixe L (2019)
Publication Type: Conference contribution
Publication year: 2019
Publisher: Institute of Electrical and Electronics Engineers Inc.
Pages Range: 4497-4503
Conference Proceedings Title: IEEE International Conference on Intelligent Robots and Systems
Event location: Macau, CHN
ISBN: 9781728140049
DOI: 10.1109/IROS40897.2019.8968451
The ability of deep learning models to generalize well across different scenarios depends primarily on the quality and quantity of annotated data. Labeling large amounts of data for all possible scenarios that a model may encounter would not be feasible; if even possible. We propose a framework to deal with limited labeled training data and demonstrate it on the application of vision-based vehicle control. We show how limited steering angle data available for only one condition can be transferred to multiple different weather scenarios. This is done by leveraging unlabeled images in a teacher-student learning paradigm complemented with an image-to-image translation network. The translation network transfers the images to a new domain, whereas the teacher provides soft supervised targets to train the student on this domain. Furthermore, we demonstrate how utilization of auxiliary networks can reduce the size of a model at inference time, without affecting the accuracy. The experiments show that our approach generalizes well across multiple different weather conditions using only ground truth labels from one domain.
APA:
Khan, Q., Wenzel, P., Cremers, D., & Leal-Taixe, L. (2019). Towards Generalizing Sensorimotor Control Across Weather Conditions. In IEEE International Conference on Intelligent Robots and Systems (pp. 4497-4503). Macau, CHN: Institute of Electrical and Electronics Engineers Inc..
MLA:
Khan, Qadeer, et al. "Towards Generalizing Sensorimotor Control Across Weather Conditions." Proceedings of the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2019, Macau, CHN Institute of Electrical and Electronics Engineers Inc., 2019. 4497-4503.
BibTeX: Download