Abstract
The paper focuses on maximizing feature extraction and classification using one-shot learning (meta-learning). The present work discusses how to maximize the performance of the Siamese Neural Network using various regularization and normalization techniques for very low epochs. In this paper we perform multi-class Face Recognition. A unique pairing of face images helps us to understand the generalization capacity of our network which is scrutinized on AT&T-ORL face databases. We performed experiments to see how learning can be made to converge within a few epochs, and the approach has also made a telling performance on unseen test data which is about 96.01%. Besides, we discuss the ways to speed up learning particularly for a Siamese network and achieve convergence within 5 epochs. We found one of the better regularization techniques for fast reduction of the loss function. It is apparent from our findings that only normalization is the effective approach while working within less epochs. Also, Dropout After Batch Normalization configuration results in smooth loss reduction.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Abbreviations
- BD:
-
Dropout After Batch Normalization
- DB:
-
Batch Normalization After Dropout
- BN:
-
Batch normalization,
- FV:
-
Face Verification
References
Duan T, Lu J, Feng J, Zhou J (2017) Context-aware local binary feature learning for face recognition. IEEE Trans Pattern Analysis Mach Intell PP(99):1–1
Xu Y, Li Z, Yang J, Zhang D A survey of dictionary learning algorithms for face recognition. IEEE Access 5:8
Guo G, Li SZ, Chan K (2000) Face recognition by support vector machines. In: 4th IEEE international conference on automatic face and gesture recognition, pp 196
Chopra S, Hadsell R, LeCun Y (2005) Learning a similarity metric discriminatively, with application to FV. In: IEEE computer society conference on computer vision & pattern recognition, CVPR 2005, pp 539–546
Hassan G, Elgazzar K (2016) The case of face-recognition on mobile devices. In: 2016 IEEE wireless communications and networking conference, pp 1–6
Koch G (2015) Siamese neural networks for one-shot image recognition. Accessed August 2018
David et al., “Learning Representations by back propagating errors”, Nature 1986 pp 533
Szegedy et al Going deeper with convolutions CVPR’ 15
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition published at ICLR conference
Taigman Y et al (2014) DeepFace-Closing the gap to human-level performance in FV. In: Conference on Computer Vision and Pattern Recognition (CVPR)
Srivastava N (2015) Dropout: a simple way to prevent neural networks from overfitting
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. ICML 37:448
Ahlawat S et al (2018) Hand gesture recognition using convolutional neural network. In: International conference on innovative computing and communications, pp 179–186
Sharma P et al (2018) Leaf Identification Using HOG, KNN, and neural networks. In: International conference on innovative computing and communications pp 83–91
The Database of Face available at: https://www.cl.cam.ac.uk/research/dtg/attarchive/facedatabase.html
Viola P et al (2001) Rapid object detection using a boosted cascade of simple features. CVPR 2001
Haar like features, Available at wiki: https://en.m.wikipedia.org/wiki/Haar-like_feature. Accessed Dec 2018
Rmsprop available at coursera: https://www.coursera.org/learn/neural-networks/lecture/YQHki/rmsprop-divide-the- gradient-by-a-running-average-of-its-recent-magnitude
Xavier G, Bengio Y (2010) Understanding the difficulty of training deep feed forward neural networks. Aistats 9
Google Colab available at: https://colab.research.google.com/. Accessed Aug–Dec 2018
Acknowledgements
We acknowledge AT&T Laboratories Cambridge for images used in this work. We also acknowledge Amit Chakraborty and Anirban Dan, coauthors of this paper, for giving consent to use their data in this work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chakraborty, N., Dan, A., Chakraborty, A., Neogy, S. (2020). Effect of Dropout and Batch Normalization in Siamese Network for Face Recognition. In: Khanna, A., Gupta, D., Bhattacharyya, S., Snasel, V., Platos, J., Hassanien, A. (eds) International Conference on Innovative Computing and Communications. Advances in Intelligent Systems and Computing, vol 1059. Springer, Singapore. https://doi.org/10.1007/978-981-15-0324-5_3
Download citation
DOI: https://doi.org/10.1007/978-981-15-0324-5_3
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-0323-8
Online ISBN: 978-981-15-0324-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)