The First Principles of Deep Learning and Compression

TL;DR

This paper explores how integrating first principles and prior engineering knowledge into deep learning models can enhance multimedia compression, improving fidelity without replacing classical algorithms like JPEG and MPEG.

Contribution

It introduces a novel approach that leverages first principles to improve deep learning-based multimedia compression, bridging the gap between academic success and industry adoption.

Findings

First principles-based methods outperform general deep learning models in compression fidelity.

Incorporating prior knowledge improves performance without replacing classical algorithms.

The approach enhances the practicality of deep learning for industry use in multimedia compression.

Abstract

The deep learning revolution incited by the 2012 Alexnet paper has been transformative for the field of computer vision. Many problems which were severely limited using classical solutions are now seeing unprecedented success. The rapid proliferation of deep learning methods has led to a sharp increase in their use in consumer and embedded applications. One consequence of consumer and embedded applications is lossy multimedia compression which is required to engineer the efficient storage and transmission of data in these real-world scenarios. As such, there has been increased interest in a deep learning solution for multimedia compression which would allow for higher compression ratios and increased visual quality. The deep learning approach to multimedia compression, so called Learned Multimedia Compression, involves computing a compressed representation of an image or video using a deep network for the encoder and the decoder. While these techniques have enjoyed impressive academic success, their industry adoption has been essentially non-existent. Classical compression techniques like JPEG and MPEG are too entrenched in modern computing to be easily replaced. This dissertation takes an orthogonal approach and leverages deep learning to improve the compression fidelity of these classical algorithms. This allows the incredible advances in deep learning to be used for multimedia compression without threatening the ubiquity of the classical methods. The key insight of this work is that methods which are motivated by first principles, i.e., the underlying engineering decisions that were made when the compression algorithms were developed, are more effective than general methods. By encoding prior knowledge into the design of the algorithm, the flexibility, performance, and/or accuracy are improved at the cost of generality...