Abstract
Supervised learning tends to produce more accurate classifiers than unsupervised learning in general. This implies that training data is preferred with annotations. When addressing visual perception challenges, such as localizing certain object classes within an image, the learning of the involved classifiers turns out to be a practical bottleneck. The reason is that, at least, we have to frame object examples with bounding boxes in thousands of images. A priori, the more complex the model is regarding its number of parameters, the more annotated examples are required. This annotation task is performed by human oracles, which ends up in inaccuracies and errors in the annotations (aka ground truth) since the task is inherently very cumbersome and sometimes ambiguous. As an alternative, we have pioneered the use of virtual worlds for collecting such annotations automatically and with high precision. However, since the models learned with virtual data must operate in the real world, we still need to perform domain adaptation (DA). In this chapter, we revisit the DA of a Deformable Part-Based Model (DPM) as an exemplifying case of virtual- to real-world DA. As a use case, we address the challenge of vehicle detection for driver assistance, using different publicly available virtual-world data. While doing so, we investigate questions such as how does the domain gap behave due to virtual-vs-real data with respect to dominant object appearance per domain, as well as the role of photo-realism in the virtual world .
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
With this technique we won the first pedestrian detection challenge of the KITTI benchmark suite, a part of the Recognition Meets Reconstruction Challenge held in ICCV’13.
- 2.
Dataset available at http://www.xrce.xerox.com/Research-Development/Computer-Vision/Proxy-Virtual-Worlds.
- 3.
Dataset available at http://synthia-dataset.net.
- 4.
See Fig. 13.2 for a pictorial intuition.
- 5.
The reader is referred to [544] for the mathematical technical details.
- 6.
See http://unity3d.com.
- 7.
The number of vehicles mentioned in Table 13.1 refer to moderate cases.
- 8.
It is a fallacy to believe that, because good datasets are big, then big datasets are good [34].
Acknowledgements
Authors want to thank the next funding bodies: the Spanish MEC Project TRA2014-57088-C2-1-R, the People Programme (Marie Curie Actions) FP7/2007-2013 REA grant agreement no. 600388, and by the Agency of Competitiveness for Companies of the Government of Catalonia, ACCIO, the Generalitat de Catalunya Project 2014-SGR-1506 and the NVIDIA Corporation for the generous support in the form of different GPU hardware units.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this chapter
Cite this chapter
López, A.M., Xu, J., Gómez, J.L., Vázquez, D., Ros, G. (2017). From Virtual to Real World Visual Perception Using Domain Adaptation—The DPM as Example. In: Csurka, G. (eds) Domain Adaptation in Computer Vision Applications. Advances in Computer Vision and Pattern Recognition. Springer, Cham. https://doi.org/10.1007/978-3-319-58347-1_13
Download citation
DOI: https://doi.org/10.1007/978-3-319-58347-1_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-58346-4
Online ISBN: 978-3-319-58347-1
eBook Packages: Computer ScienceComputer Science (R0)