# HiDE: Hierarchical Dictionary-Based Entropy Modeling for Learned Image Compression

arXiv: https://arxiv.org/abs/2603.06766 · HTML: https://mlsanity.com/paper/2603.06766/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 32 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Builds on (most cited first, 22 of 22)

- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding](https://mlsanity.com/paper/2203.10886/) (2022)
- [Channel-wise Autoregressive Entropy Models for Learned Image Compression](https://mlsanity.com/paper/2007.08739/) (2020)
- [Learned Image Compression with Mixed Transformer-CNN Architectures](https://mlsanity.com/paper/2303.14978/) (2023)
- [Checkerboard Context Model for Efficient Learned Image Compression](https://mlsanity.com/paper/2103.15306/) (2021)
- [Nonlinear Transform Coding](https://mlsanity.com/paper/2007.03034/) (2020)
- [MLIC: Multi-Reference Entropy Model for Learned Image Compression](https://mlsanity.com/paper/2211.07273/) (2022)
- [Addressing Representation Collapse in Vector Quantized Models with One Linear Layer](https://mlsanity.com/paper/2411.02038/) (2024)
- [MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compression](https://mlsanity.com/paper/2307.15421/) (2023)
- [Frequency-Aware Transformer for Learned Image Compression](https://mlsanity.com/paper/2310.16387/) (2023)
- [Learned Image Compression with Dictionary-based Entropy Model](https://mlsanity.com/paper/2504.00496/) (2025)
- [Linear Attention Modeling for Learned Image Compression](https://mlsanity.com/paper/2502.05741/) (2025)
- [MambaIC: State Space Models for High-Performance Learned Image Compression](https://mlsanity.com/paper/2503.12461/) (2025)
- [Causal Context Adjustment Loss for Learned Image Compression](https://mlsanity.com/paper/2410.04847/) (2024)
- [Image-Dependent Local Entropy Models for Learned Image Compression](https://mlsanity.com/paper/1805.12295/) (2018)
- [Conditional Latent Coding with Learnable Synthesized Reference for Deep Image Compression](https://mlsanity.com/paper/2502.09971/) (2025)
- [Channel-Level Variable Quantization Network for Deep Image Compression](https://mlsanity.com/paper/2007.12619/) (2020)

## Abstract (arXiv)

Learned image compression (LIC) has achieved remarkable coding efficiency, where entropy modeling plays a pivotal role in minimizing bitrate through informative priors. Existing methods predominantly exploit internal contexts within the input image, yet the rich external priors embedded in large-scale training data remain largely underutilized. Recent advances in dictionary-based entropy models have demonstrated that incorporating external priors can substantially enhance compression performance. However, current approaches organize heterogeneous external priors within a single-level dictionary, resulting in imbalanced utilization and limited representational capacity. Moreover, effective entropy modeling requires not only expressive priors but also a parameter estimation network capable of interpreting them. To address these challenges, we propose HiDE, a Hierarchical Dictionary-based Entropy modeling framework for learned image compression. HiDE decomposes external priors into global structural and local detail dictionaries with cascaded retrieval, enabling structured and efficient utilization of external information. Moreover, a context-aware parameter estimator with parallel multi-receptive-field design is introduced to adaptively exploit heterogeneous contexts for accurate conditional probability estimation. Experimental results show that HiDE achieves 18.5%, 21.99%, and 24.01% BD-rate savings over VTM-12.1 on the Kodak, CLIC, and Tecnick datasets, respectively.