Learned Image Compression with Dictionary-based Entropy Model

2025-04-01

AI Summary

Existing learned image compression methods employ entropy models—such as hyperpriors or autoregressive models—that capture only latent-space dependencies, neglecting structured priors inherent in training data. This work proposes the Dictionary-driven Cross-Attention Entropy Model (DCA-EM), the first entropy model to incorporate a learnable structural dictionary, explicitly modeling canonical local structural priors from training data. DCA-EM fuses data-level structural priors with latent-space dependencies via cross-attention, enabling end-to-end differentiability and rate-distortion joint optimization. Evaluated on standard benchmarks, DCA-EM achieves state-of-the-art performance, significantly outperforming both VVC and leading learned compression approaches. Crucially, it delivers superior compression quality while maintaining low inference latency—demonstrating a favorable trade-off between efficiency and fidelity.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Learning & Optimization for CV
• Data Mining & Knowledge Management: Data Compression

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Learned image compression methods have attracted great research interest and exhibited superior rate-distortion performance to the best classical image compression standards of the present. The entropy model plays a key role in learned image compression, which estimates the probability distribution of the latent representation for further entropy coding. Most existing methods employed hyper-prior and auto-regressive architectures to form their entropy models. However, they only aimed to explore the internal dependencies of latent representation while neglecting the importance of extracting prior from training data. In this work, we propose a novel entropy model named Dictionary-based Cross Attention Entropy model, which introduces a learnable dictionary to summarize the typical structures occurring in the training dataset to enhance the entropy model. Extensive experimental results have demonstrated that the proposed model strikes a better balance between performance and latency, achieving state-of-the-art results on various benchmark datasets.

Problem

• Improving entropy models in learned image compression
• Enhancing latent representation probability estimation
• Balancing performance and latency in compression

Innovation

• Learned dictionary enhances entropy model
• Cross attention improves latent representation
• Balances performance and latency effectively