Scalable Image Coding for Humans and Machines Using Feature Fusion Network

TL;DR

This paper introduces a scalable image coding method that efficiently combines models for humans and machines using feature fusion, enabling versatile image compression across various recognition models with reduced parameters.

Contribution

A novel learning-based scalable image coding approach that fuses multiple compression models for humans and machines, adaptable to various recognition models and optimized for fewer parameters.

Findings

Effective image compression with high quality and low bitrate.

Feature fusion network reduces model parameters.

Compatible with multiple image recognition models.

Abstract

As image recognition models become more prevalent, scalable coding methods for machines and humans gain more importance. Applications of image recognition models include traffic monitoring and farm management. In these use cases, the scalable coding method proves effective because the tasks require occasional image checking by humans. Existing image compression methods for humans and machines meet these requirements to some extent. However, these compression methods are effective solely for specific image recognition models. We propose a learning-based scalable image coding method for humans and machines that is compatible with numerous image recognition models. We combine an image compression model for machines with a compression model, providing additional information to facilitate image decoding for humans. The features in these compression models are fused using a feature fusion network to achieve efficient image compression. Our method's additional information compression model is adjusted to reduce the number of parameters by enabling combinations of features of different sizes in the feature fusion network. Our approach confirms that the feature fusion network efficiently combines image compression models while reducing the number of parameters. Furthermore, we demonstrate the effectiveness of the proposed scalable coding method by evaluating the image compression performance in terms of decoded image quality and bitrate.