Image Coding for Machines with Object Region Learning

TL;DR

This paper introduces a novel image compression model that learns object regions without needing extra input or task-specific loss, enabling versatile image coding for various recognition models.

Contribution

The proposed model learns object regions directly, eliminating the need for ROI-maps or task-loss, thus supporting multiple image recognition models with a single compression approach.

Findings

Effective across multiple recognition models

Versatile for different datasets

Outperforms previous methods in experiments

Abstract

Compression technology is essential for efficient image transmission and storage. With the rapid advances in deep learning, images are beginning to be used for image recognition as well as for human vision. For this reason, research has been conducted on image coding for image recognition, and this field is called Image Coding for Machines (ICM). There are two main approaches in ICM: the ROI-based approach and the task-loss-based approach. The former approach has the problem of requiring an ROI-map as input in addition to the input image. The latter approach has the problems of difficulty in learning the task-loss, and lack of robustness because the specific image recognition model is used to compute the loss function. To solve these problems, we propose an image compression model that learns object regions. Our model does not require additional information as input, such as an ROI-map, and does not use task-loss. Therefore, it is possible to compress images for various image recognition models. In the experiments, we demonstrate the versatility of the proposed method by using three different image recognition models and three different datasets. In addition, we verify the effectiveness of our model by comparing it with previous methods.