Efficient Nonlinear Transforms for Lossy Image Compression

We assess the performance of two techniques in the context of nonlinear transform coding with artificial neural networks, Sadam and GDN. Both techniques have been success- fully used in state-of-the-art image compression methods, but their performance has not been individually assessed to this point. Together, the techniques stabilize the training procedure of nonlinear image transforms and increase their capacity to approximate the (unknown) rate-distortion optimal transform functions. Besides comparing their performance to established alternatives, we detail the implementation of both methods and provide open-source code along with the paper.

[1]  M. Carandini,et al.  Normalization as a canonical neural computation , 2013, Nature Reviews Neuroscience.

[2]  Lucas Theis,et al.  Lossy Image Compression with Compressive Autoencoders , 2017, ICLR.

[3]  Valero Laparra,et al.  Density Modeling of Images using a Generalized Normalization Transformation , 2015, ICLR.

[4]  D J Field,et al.  Relations between the statistics of natural images and the response properties of cortical cells. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[5]  Luca Benini,et al.  Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations , 2017, NIPS.

[6]  David Minnen,et al.  Full Resolution Image Compression with Recurrent Neural Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  David Minnen,et al.  Variable Rate Image Compression with Recurrent Neural Networks , 2015, ICLR.

[8]  Valero Laparra,et al.  End-to-end Optimized Image Compression , 2016, ICLR.

[9]  David Minnen,et al.  Variational image compression with a scale hyperprior , 2018, ICLR.

[10]  Klaus-Robert Müller,et al.  Efficient BackProp , 2012, Neural Networks: Tricks of the Trade.

[11]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[12]  Siwei Lyu.  Divisive Normalization: Justification and Effectiveness as Efficient Coding Transform , 2010, NIPS.

[13]  Lubomir D. Bourdev,et al.  Real-Time Adaptive Image Compression , 2017, ICML.

[14]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[15]  N. Ahmed,et al.  Discrete Cosine Transform , 1996 .

[16]  Allan Pinkus,et al.  Multilayer Feedforward Networks with a Non-Polynomial Activation Function Can Approximate Any Function , 1991, Neural Networks.

[17]  Valero Laparra,et al.  Psychophysically Tuned Divisive Normalization Approximately Factorizes the PDF of Natural Images , 2010, Neural Computation.

[18]  Valero Laparra,et al.  End-to-end optimization of nonlinear transform codes for perceptual quality , 2016, 2016 Picture Coding Symposium (PCS).