Abstract
Image compression has a long history, being widely applied in numerous applications. Yet, the commonly applied approach is based on traditional signal processing, such as JPEG. The lack of learning process in the approach limits the performance of those methods. Deep learning, recently, shows great performance in image compression, whose success may be attributed to various factors. Activation function is known as one of these influential factors. The present work is devoted to analyze the different effects of various activation functions, and the experimental results suggest that the generalized divisive normalization (GDN) is probably the best activation function in deep image approach-based image compression.
Authors Qiang Duan, Xue Li and Qingshan Yin contributed equally to this study.
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
References
Agustsson E, Tschannen M, Mentzer F, Timofte R, Van Gool L (2019) Generative adversarial networks for extreme learned image compression. In: Proceedings of the IEEE international conference on computer vision, pp 221–231
Ballé J, Laparra V, Simoncelli EP (2016) Density modeling of images using a generalized normalization transformation. In: 4th international conference on learning representations, ICLR
Ballé J, Laparra V, Simoncelli EP (2016) End-to-end optimized image compression. arXiv:1611.01704
Dong C, Loy CC, He K, Tang X (2014) Learning a deep convolutional network for image super-resolution. In: European conference on computer vision. Springer, pp 184–199
Ignatov A, Timofte R et al (2019) PIRM challenge on perceptual image enhancement on smartphones: report. In: European conference on computer vision (ECCV) workshops, Jan 2019
Klambauer G, Unterthiner T, Mayr A, Hochreiter S (2017) Self-normalizing neural networks. In: Advances in neural information processing systems, pp 971–980
Luo S, Yang Y, Yin Y, Shen C, Zhao Y, Song M (2018) DeepSIC: deep semantic image compression. In: International conference on neural information processing. Springer, pp 96–106
Minnen D, Ballé J, Toderici GD (2018) Joint autoregressive and hierarchical priors for learned image compression. In: Advances in neural information processing systems, pp 10771–10780
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556
Toderici G, O’Malley SM, Hwang SJ, Vincent D, Minnen D, Baluja S, Covell M, Sukthankar R (2016) Variable rate image compression with recurrent neural networks. In: The international conference on learning representations
Zhou L, Sun Z, Wu X, Wu J (2019) End-to-end optimized image compression with attention mechanism. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Duan, Q. et al. (2022). A Study on the Generalized Normalization Transformation Activation Function in Deep Learning Based Image Compression. In: Yang, XS., Sherratt, S., Dey, N., Joshi, A. (eds) Proceedings of Sixth International Congress on Information and Communication Technology. Lecture Notes in Networks and Systems, vol 235. Springer, Singapore. https://doi.org/10.1007/978-981-16-2377-6_33
Download citation
DOI: https://doi.org/10.1007/978-981-16-2377-6_33
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-2376-9
Online ISBN: 978-981-16-2377-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)