Coarse-to-Fine: Progressive Image Compression for Semantically Hierarchical Classification

TL;DR

This paper introduces a semantic hierarchy-aware progressive image codec that enables coarse-to-fine classification from a single bitstream, improving recognition accuracy at various bitrate levels by leveraging semantic hierarchies.

Contribution

It proposes a novel semantic scalability framework for image compression that explicitly optimizes for hierarchical semantic classes, enhancing task-adaptive image coding.

Findings

Improves coarse-level recognition accuracy at low bitrates.

Maintains fine-grained classification performance at higher bitrates.

Outperforms existing progressive codecs in hierarchical evaluation.

Abstract

Recent advances in learned image compression (LIC) have enabled practical deployments, spurring active research into image compression for machines and progressive coding schemes. However, their integration remains under-explored: prior works on progressive machine codec predominantly target sample-level difficulty adaptation (i.e., easy-to-hard), without considering semantic-level scalability. In this work, we introduce a semantic hierarchy-aware progressive codec that enables semantic scalability (i.e., coarse-to-fine) from a single bitstream. We first systematically categorize ImageNet-1K classes into CLIP embedding-based semantic hierarchies. Based on a channel-wise autoregressive framework, we decompose latent representations into hierarchically ordered channel blocks, each explicitly optimized for a corresponding semantic hierarchy. Extensive experiments demonstrate that our approach substantially improves coarse-level recognition at low bitrates while maintaining fine-grained accuracy at higher bitrates. By reframing progressive transmission through the lens of semantic scalability, our work provides an efficient and interpretable solution for task-adaptive image coding, outperforming existing progressive codecs under hierarchical evaluation.