skip to main content
10.1145/3177148.3180085acmotherconferencesArticle/Chapter ViewAbstractPublication PagesmedpraiConference Proceedingsconference-collections
research-article

Curriculum Learning for Depth Estimation with Deep Convolutional Neural Networks

Published: 27 March 2018 Publication History

Abstract

Curriculum learning is a machine learning technique adapted from the way humans acquire knowledge and skills, initially mastering simple tasks and progressing to more complex tasks. The work explores curriculum training by creating multiple levels of dataset with increasing complexity on which the trainings are performed. The experiments demonstrated that there is an average of 12% improvement test loss when compared to a non-curriculum approach. The experiment also demonstrates the advantage of creating synthetic dataset and how it aids in the overall improvement of accuracy. An improvement of 26% is attained on the test error loss when curriculum trained model was compared to training on a limited real world dataset. The work also goes onto propose a novel learning approach, the Self Paced Learning approach with Error-Diversity (SPL-ED) An overall reduction of 32% in the test loss is observed when compared to the non-curriculum training limited to real-world dataset.

References

[1]
Yoshua Bengio, Jérôme Louradour, Ronan Collobert, and Jason Weston. 2009. Curriculum Learning. In Proceedings of the 26th Annual International Conference on Machine Learning (ICML '09). ACM, New York, NY, USA, 41--48.
[2]
Gabriel J. Brostow, Julien Fauqueur, and Roberto Cipolla. 2008. Semantic Object Classes in Video: A High-Definition Ground Truth Database. Pattern Recognition Letters xx, x (2008), xx--xx.
[3]
David A. Cohn, Zoubin Ghahramani, and Michael I. Jordan. 1996. Active Learning with Statistical Models. CoRR cs.AI/9603104 (1996). http://arxiv.org/abs/cs.AI/9603104
[4]
Blender Online Community. {n. d.}. Blender - a 3D modelling and rendering package. Blender Foundation, Blender Institute, Amsterdam. http://www.blender.org
[5]
Marius Cordts, Mohamed Omran, Sebastian Ramos, Timo Rehfeld, Markus Enzweiler, Rodrigo Benenson, Uwe Franke, Stefan Roth, and Bernt Schiele. 2016. The Cityscapes Dataset for Semantic Urban Scene Understanding. CoRR abs/1604.01685 (2016). http://arxiv.org/abs/1604.01685
[6]
David Eigen, Christian Puhrsch, and Rob Fergus. 2014. Depth map prediction from a single image using a multi-scale deep network (january ed.). Vol. 3. Neural information processing systems foundation, 2366--2374.
[7]
Andreas Geiger, Philip Lenz, Christoph Stiller, and Raquel Urtasun. 2013. Vision meets Robotics: The KITTI Dataset. International Journal of Robotics Research (IJRR) (2013).
[8]
Galen Hunt and Doug Brubacher. 1999. Detours: Binary Interception of Win32 Functions. In Proceedings of the 3rd Conference on USENIX Windows NT Symposium - Volume 3 (WINSYM'99). USENIX Association, Berkeley, CA, USA, 14--14. http://dl.acm.org/citation.cfm?id=1268427.1268441
[9]
Lu Jiang, Deyu Meng, Shoou-I Yu, Zhenzhong Lan, Shiguang Shan, and Alexander G. Hauptmann. 2014. Self-paced Learning with Diversity. In Proceedings of the 27th International Conference on Neural Information Processing Systems (NIPS'14). MIT Press, Cambridge, MA, USA, 2078--2086. http://dl.acm.org/citation.cfm?id=2969033.2969059
[10]
Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In Advances in Neural Information Processing Systems 25, F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger (Eds.). Curran Associates, Inc., 1097--1105. http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf
[11]
M. P. Kumar, Benjamin Packer, and Daphne Koller. 2010. Self-Paced Learning for Latent Variable Models. In Advances in Neural Information Processing Systems 23, J. D. Lafferty, C. K. I. Williams, J. Shawe-Taylor, R. S. Zemel, and A. Culotta (Eds.). Curran Associates, Inc., 1189--1197. http://papers.nips.cc/paper/3923-self-paced-learning-for-latent-variable-models.pdf
[12]
Miaomiao Liu, Mathieu Salzmann, and Xuming He. 2014. Discrete-Continuous Depth Estimation from a Single Image. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[13]
Pushmeet Kohli Nathan Silberman, Derek Hoiem and Rob Fergus. 2012. Indoor Segmentation and Support Inference from RGBD Images. In ECCV.
[14]
Stephan R. Richter, Vibhav Vineet, Stefan Roth, and Vladlen Koltun. 2016. Playing for Data: Ground Truth from Computer Games. CoRR abs/1608.02192 (2016). http://arxiv.org/abs/1608.02192
[15]
Ashutosh Saxena, Min Sun, and Andrew Y. Ng. 2009. Make3D: Learning 3D Scene Structure from a Single Still Image. IEEE Trans. Pattern Anal. Mach. Intell. 31, 5 (May 2009), 824--840.

Cited By

View all
  • (2022)Density-Aware Curriculum Learning for Crowd CountingIEEE Transactions on Cybernetics10.1109/TCYB.2020.303342852:6(4675-4687)Online publication date: Jun-2022

Index Terms

  1. Curriculum Learning for Depth Estimation with Deep Convolutional Neural Networks

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    MedPRAI '18: Proceedings of the 2nd Mediterranean Conference on Pattern Recognition and Artificial Intelligence
    March 2018
    135 pages
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

    In-Cooperation

    • IAPR: International Association for Pattern Recognition

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 27 March 2018

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. Curriculum Learning
    2. Depth Estimation

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Conference

    MedPRAI '18

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)4
    • Downloads (Last 6 weeks)2
    Reflects downloads up to 17 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2022)Density-Aware Curriculum Learning for Crowd CountingIEEE Transactions on Cybernetics10.1109/TCYB.2020.303342852:6(4675-4687)Online publication date: Jun-2022

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media