Universal Rate-Distortion-Perception Representations for Lossy Compression

06/18/2021
by   George Zhang, et al.
0

In the context of lossy compression, Blau Michaeli (2019) adopt a mathematical notion of perceptual quality and define the information rate-distortion-perception function, generalizing the classical rate-distortion tradeoff. We consider the notion of universal representations in which one may fix an encoder and vary the decoder to achieve any point within a collection of distortion and perception constraints. We prove that the corresponding information-theoretic universal rate-distortion-perception function is operationally achievable in an approximate sense. Under MSE distortion, we show that the entire distortion-perception tradeoff of a Gaussian source can be achieved by a single encoder of the same rate asymptotically. We then characterize the achievable distortion-perception region for a fixed representation in the case of arbitrary distributions, identify conditions under which the aforementioned results continue to hold approximately, and study the case when the rate is not fixed in advance. This motivates the study of practical constructions that are approximately universal across the RDP tradeoff, thereby alleviating the need to design a new encoder for each objective. We provide experimental results on MNIST and SVHN suggesting that on image compression tasks, the operational tradeoffs achieved by machine learning models with a fixed encoder suffer only a small penalty when compared to their variable encoder counterparts.

READ FULL TEXT

page 9

page 12

page 29

research
01/23/2019

Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff

Lossy compression algorithms are typically designed and analyzed through...
research
05/30/2023

On the Choice of Perception Loss Function for Learned Video Compression

We study causal, low-latency, sequential video compression when the outp...
research
11/30/2018

Rate-Distortion-Perception Tradeoff of Variable-Length Source Coding for General Information Sources

Blau and Michaeli recently introduced a novel concept for inverse proble...
research
02/27/2020

A Free-Energy Principle for Representation Learning

This paper employs a formal connection of machine learning with thermody...
research
02/08/2022

The Rate-Distortion-Perception Tradeoff: The Role of Common Randomness

A rate-distortion-perception (RDP) tradeoff has recently been proposed b...
research
05/22/2023

The Rate-Distortion-Perception Trade-off with Side Information

In image compression, with recent advances in generative modeling, the e...
research
04/18/2019

On The Classification-Distortion-Perception Tradeoff

Signal degradation is ubiquitous and computational restoration of degrad...

Please sign up or login with your details

Forgot password? Click here to reset