3D Object Recognition Using Convolutional Neural Networks with Transfer Learning Between Input Channels
RGB-D data is getting ever more interest from the research community as both cheap cameras appear in the market and the applications of this type of data become more common. A current trend in processing image data is the use of convolutional neural networks (CNNs) that have consistently beat competition in most benchmark data sets. In this paper, we investigate the possibility of transferring knowledge between CNNs when processing RGB-D data with the goal of both improving accuracy and reducing training time. We present experiments that show that our proposed approach can achieve both these goals.
Keywords3D object recognition Transfer learning Convolutional neural networks
This work was partially financed by FEDER funds through the “Programa Operacional Factores de Competitividade—COMPETE” and by Portuguese funds through “FCT—Fundação para a Ciência e a Tecnologia” in the framework of the project PTDC/EIA-EIA/119004/2010 and PEst-OE/EEI/LA0008/2013.
- 1.Pronobis, A., Mozos, O.M., Caputo, B., Jensfelt, P.: Multi-modal semantic place classification. I. J. Robotic Res. 29(2–3) (2010) 298–320.Google Scholar
- 2.Alexandre, L.A.: 3D descriptors for object and category recognition: a comparative evaluation. In: Workshop on Color-Depth Camera Fusion in Robotics at the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vilamoura, Portugal (October 2012).Google Scholar
- 3.Bengio, Y.: Learning deep architectures for AI. Foundations and Trends in Machine Learning 2(1) (2009) 1–127.Google Scholar
- 6.Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: Machine Learning, Proceedings of the Twenty-Fifth International Conference (ICML 2008), Helsinki, Finland, June 5–9, 2008. (2008) 1096–1103.Google Scholar
- 7.LeCun, Y., Bengio, Y.: Convolutional networks for images, speech, and time-series. In Arbib, M.A., ed.: The Handbook of Brain Theory and Neural Networks, MIT Press (1995).Google Scholar
- 8.Ciresan, D.C., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA (June 2012) 3642–3649.Google Scholar
- 9.Filipe, S., Alexandre, L.A.: From the human visual system to the computational models of visual attention: A survey. Artificial Intelligence Review (January 2013) 1–47.Google Scholar
- 11.Socher, R., Huval, B., Bath, B., Manning, C., Ng, A.: Convolutional-recursive deep learning for 3d object classification. In Bartlett, P., Pereira, F., Burges, C., Bottou, L., Weinberger, K., eds.: Advances in Neural Information Processing Systems 25. (2012) 665–673.Google Scholar
- 13.Ciresan, D.C., Meier, U., Schmidhuber, J.: Transfer learning for latin and chinese characters with deep neural networks. In: The 2012 International Joint Conference on Neural Networks, Brisbane, Australia (June 2012) 1301–1306.Google Scholar
- 14.Amaral, T., Sá, J., Silva, L., Alexandre, L.A., Santos, J.: Improving performance on problems with few labelled data by reusing stacked auto-encoders. In: submitted. (2014).Google Scholar
- 15.Lai, K., Bo, L., Ren, X., Fox, D.: A Large-Scale hierarchical Multi-View RGB-D object dataset. In: Proc. of the IEEE International Conference on Robotics & Automation (ICRA). (2011).Google Scholar