Abstract
Flow-based neural networks are promising generative image models. One of their main drawbacks at the moment is the large number of parameters and the large size of the hidden representation of modeled data, which complicates their use on an industrial scale. This article proposes a method for isolating redundant components of vector representations generated by flow-based networks using the Glow neural network as an example to the face generation problem, which has shown effective ten times compression. The prospects of using such compression for more efficient parallelization of training and inference using model parallelism are considered.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ballard DH (1987) Modular learning in neural networks. In: AAAI, pp 279–284
Deza MM, Deza E (2009) Encyclopedia of distances. In: Encyclopedia of distances. Springer, Berlin, pp 1–583
Dinh L, Krueger D, Bengio Y (2014) Nice: Non-linear independent components estimation. arXiv preprint arXiv:1410.8516
Dinh L, Sohl-Dickstein J, Bengio S (2016) Density estimation using real NVP. arXiv preprint arXiv:1605.08803
Hore A, Ziou D (2010) Image quality metrics: PSNR vs. SSIM. In: 2010 20th international conference on pattern recognition. IEEE, New York, pp 2366–2369
Karras T, Laine S, Aila T (2019) A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4401–4410
Kingma DP, Welling M (2013) Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114
Kingma DP, Dhariwal P (2018) Glow: generative flow with invertible \(1 \times 1\) convolutions. In: Advances in neural information processing systems, pp 10,215–10,224
Kumar M, Babaeizadeh M, Erhan D, Finn C, Levine S, Dinh L, Kingma D (2019) Videoflow: a flow-based generative model for video. arXiv preprint arXiv:1903.01434
Liu PY, Lam EY (2018) Image reconstruction using deep learning. arXiv preprint arXiv:1809.10410
Partridge M, Calvo RA (1998) Fast dimensionality reduction and simple PCA. Intell Data Anal 2(3):203–214
Prenger R, Valle R, Catanzaro B (2019) Waveglow: a flow-based generative network for speech synthesis. In: ICASSP 2019-2019 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, New York, pp 3617–3621
Sharma G, Wu W, Dalal EN (2005) The ciede2000 color-difference formula: Implementation notes, supplementary test data, and mathematical observations. Color Research & Application: Endorsed by Inter-Society Color Council, The Colour Group (Great Britain), Canadian Society for Color, Color Science Association of Japan, Dutch Society for the Study of Color, The Swedish Colour Centre Foundation, Colour Society of Australia, Centre Français de la Couleur 30(1), 21–30
Zhang K, Zhang Z, Cheng CW, Hsu WH, Qiao Y, Liu W, Zhang T (2018) Super-identity convolutional neural network for face hallucination. In: Proceedings of the European conference on computer vision (ECCV), pp 183–198
Acknowledgements
This research work was supported by the Academic Excellence Project 5-100 proposed by Peter the Great St. Petersburg Polytechnic University.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Poliakov, S., Belykh, I. (2021). Dimensionality Reduction for Flow-Based Face Embeddings. In: Tripathy, A., Sarkar, M., Sahoo, J., Li, KC., Chinara, S. (eds) Advances in Distributed Computing and Machine Learning. Lecture Notes in Networks and Systems, vol 127. Springer, Singapore. https://doi.org/10.1007/978-981-15-4218-3_36
Download citation
DOI: https://doi.org/10.1007/978-981-15-4218-3_36
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-4217-6
Online ISBN: 978-981-15-4218-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)