ProgDTD: Progressive Learned Image Compression with Double-Tail-Drop Training

TL;DR

ProgDTD is a training method that converts existing learned image compression models into progressive ones, enabling images to load gradually with minimal performance loss, thereby improving user experience over slow networks.

Contribution

It introduces a novel training approach that enforces importance-based data sorting in the bottleneck, transforming non-progressive models into effective progressive image compressors.

Findings

ProgDTD achieves comparable performance to non-progressive models.

It performs on par with state-of-the-art progressive compression methods.

The method is compatible with CNN-based models without adding extra parameters.

Abstract

Progressive compression allows images to start loading as low-resolution versions, becoming clearer as more data is received. This increases user experience when, for example, network connections are slow. Today, most approaches for image compression, both classical and learned ones, are designed to be non-progressive. This paper introduces ProgDTD, a training method that transforms learned, non-progressive image compression approaches into progressive ones. The design of ProgDTD is based on the observation that the information stored within the bottleneck of a compression model commonly varies in importance. To create a progressive compression model, ProgDTD modifies the training steps to enforce the model to store the data in the bottleneck sorted by priority. We achieve progressive compression by transmitting the data in order of its sorted index. ProgDTD is designed for CNN-based learned image compression models, does not need additional parameters, and has a customizable range of progressiveness. For evaluation, we apply ProgDTDto the hyperprior model, one of the most common structures in learned image compression. Our experimental results show that ProgDTD performs comparably to its non-progressive counterparts and other state-of-the-art progressive models in terms of MS-SSIM and accuracy.