Abstract
Most of the multitask deep learning today use different but correlated tasks to improve their performances by sharing the common features of the tasks. What will happen if we use outlier tasks instead of related tasks? Will they deteriorate the performance? In this paper, we explore the influence of outlier tasks to the multitask deep learning through carefully designed experiments. We compare the accuracies and the convergence rates between the single task convolutional neural network (STCNN) and outlier multitask convolutional neural network (OMTCNN) on facial attribute recognition and hand-written digit recognition. By doing that, we prove that outlier tasks will constrain each other in a multitask network without parameter redundancy and cause a worse performance. We also discover that outlier tasks related to image recognition, like facial attribute recognition and hand-written digit recognition, may not be outlier tasks and have some common features in the bottom layers for the fact that they can use the other one’s first convolutional layer to replace theirs without any accuracy losses.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Nielsen, M.: Neural Networks and Deep Learning. Determination Press (2015)
Krizhevsky, A., Sutskever, I., Hinton, E.: ImageNet classification with deep convolutional neural networks. In: International Conference on Neural Information Processing Systems (2012)
Lecun, Y., Haffner, P.: Gradient-based Learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998)
Caruana, R.: Multitask learning. Mach. Learn. 28, 41–75 (1997)
Biswaranjan, K., Devries, T., Taylor, G.W.: Multitask learning of facial landmarks and expression. In: 2014 Canadian Conference on Computer and Robot Vision, pp. 98–103 (2014)
Zhang, Z., Luo, P., Chen, C.L., Tang, X.: Facial landmark detection by deep multitask learning. In: European Conference on Computer Vision, pp. 94–108 (2014)
Yu, B., Lane, I.: Multitask deep learning for image understanding. In: Soft Computing and Pattern Recognition, pp. 37–42. IEEE (2014)
Zhang, C., Zhang, Z.: Improving multiview face detection with multitask deep convolutional neural networks. In: IEEE Winter Conference on Applications of Computer Vision, pp. 1036–1041 (2014)
Bengio, Y.: Learning Deep Architectures for AI. Now Publishers, Hanover (2009)
Acknowledgement
The work is funded by the National Natural Science Foundation of China (No. 61170155), Shanghai Innovation Action Plan Project (No. 16511101200) and the Open Project Program of the National Laboratory of Pattern Recognition (No. 201600017).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Cai, S., Fang, Y., Ma, Z. (2017). Will Outlier Tasks Deteriorate Multitask Deep Learning?. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, ES. (eds) Neural Information Processing. ICONIP 2017. Lecture Notes in Computer Science(), vol 10635. Springer, Cham. https://doi.org/10.1007/978-3-319-70096-0_26
Download citation
DOI: https://doi.org/10.1007/978-3-319-70096-0_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-70095-3
Online ISBN: 978-3-319-70096-0
eBook Packages: Computer ScienceComputer Science (R0)