Visual Domain Adaptation for Monocular Depth Estimation on Resource-Constrained Hardware
Hornauer J, Nalpantidis L, Belagiannis V (2021)
Publication Type: Conference contribution
Publication year: 2021
Publisher: Institute of Electrical and Electronics Engineers Inc.
Book Volume: 2021-October
Pages Range: 954-962
Conference Proceedings Title: Proceedings of the IEEE International Conference on Computer Vision
Event location: Virtual, Online, CAN
ISBN: 9781665401913
DOI: 10.1109/ICCVW54120.2021.00111
Abstract
Real-world perception systems in many cases build on hardware with limited resources to adhere to cost and power limitations of their carrying system. Deploying deep neural networks on resource-constrained hardware became possible with model compression techniques, as well as efficient and hardware-aware architecture design. However, model adaptation is additionally required due to the diverse operation environments. In this work, we address the problem of training deep neural networks on resource-constrained hardware in the context of visual domain adaptation. We select the task of monocular depth estimation where our goal is to transform a pre-trained model to the target's domain data. While the source domain includes labels, we assume an unlabelled target domain, as it happens in real-world applications. Then, we present an adversarial learning approach that is adapted for training on the device with limited resources. Since visual domain adaptation, i.e. neural network training, has not been previously explored for resource-constrained hardware, we present the first feasibility study for image-based depth estimation. Our experiments show that visual domain adaptation is relevant only for efficient network architectures and training sets at the order of a few hundred samples. Models and code are publicly available1.
Authors with CRIS profile
Involved external institutions
Universität Ulm
Germany (DE)
Technical University of Denmark / Danmarks Tekniske Universitet (DTU)
Denmark (DK)
Germany (DE)
Technical University of Denmark / Danmarks Tekniske Universitet (DTU)
Denmark (DK)
How to cite
APA:
Hornauer, J., Nalpantidis, L., & Belagiannis, V. (2021). Visual Domain Adaptation for Monocular Depth Estimation on Resource-Constrained Hardware. In Proceedings of the IEEE International Conference on Computer Vision (pp. 954-962). Virtual, Online, CAN: Institute of Electrical and Electronics Engineers Inc..
MLA:
Hornauer, Julia, Lazaros Nalpantidis, and Vasileios Belagiannis. "Visual Domain Adaptation for Monocular Depth Estimation on Resource-Constrained Hardware." Proceedings of the 18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021, Virtual, Online, CAN Institute of Electrical and Electronics Engineers Inc., 2021. 954-962.
BibTeX: Download