# Diversify, Contextualize, and Adapt: Efficient Entropy Modeling for Neural Image Codec

arXiv: https://arxiv.org/abs/2411.05832 · HTML: https://mlsanity.com/paper/2411.05832/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 24 references that are in the map.
- First posted on arXiv 6 Nov 2024.

## Builds on (most cited first, 17 of 17)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [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)
- [ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding](https://mlsanity.com/paper/2203.10886/) (2022)
- [CompressAI: a PyTorch library and evaluation platform for end-to-end compression research](https://mlsanity.com/paper/2011.03029/) (2020)
- [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)
- [Neural Video Compression with Diverse Contexts](https://mlsanity.com/paper/2302.14402/) (2023)
- [The Devil Is in the Details: Window-based Attention for Image Compression](https://mlsanity.com/paper/2203.08450/) (2022)
- [Entroformer: A Transformer-based Entropy Model for Learned Image Compression](https://mlsanity.com/paper/2202.05492/) (2022)
- [MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compression](https://mlsanity.com/paper/2307.15421/) (2023)
- [Joint Global and Local Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/2112.04487/) (2021)
- [Learning Accurate Entropy Model with Global Reference for Image Compression](https://mlsanity.com/paper/2010.08321/) (2020)
- [Understanding Masked Autoencoders via Hierarchical Latent Variable Models](https://mlsanity.com/paper/2306.04898/) (2023)

## Built on by (most cited first, 3 of 3)

- [Learned Image Compression with Hierarchical Progressive Context Modeling](https://mlsanity.com/paper/2507.19125/) (2025)
- [Control Your View: High-Resolution Global Semantic Manipulation in Learned Image Compression](https://mlsanity.com/paper/2605.08727/) (2026)
- [Fast Test-Time Refinement for Robust Learned Image Compression](https://mlsanity.com/paper/2608.15113/) (2026)

## Abstract (arXiv)

Designing a fast and effective entropy model is challenging but essential for practical application of neural codecs. Beyond spatial autoregressive entropy models, more efficient backward adaptation-based entropy models have been recently developed. They not only reduce decoding time by using smaller number of modeling steps but also maintain or even improve rate--distortion performance by leveraging more diverse contexts for backward adaptation. Despite their significant progress, we argue that their performance has been limited by the simple adoption of the design convention for forward adaptation: using only a single type of hyper latent representation, which does not provide sufficient contextual information, especially in the first modeling step. In this paper, we propose a simple yet effective entropy modeling framework that leverages sufficient contexts for forward adaptation without compromising on bit-rate. Specifically, we introduce a strategy of diversifying hyper latent representations for forward adaptation, i.e., using two additional types of contexts along with the existing single type of context. In addition, we present a method to effectively use the diverse contexts for contextualizing the current elements to be encoded/decoded. By addressing the limitation of the previous approach, our proposed framework leads to significant performance improvements. Experimental results on popular datasets show that our proposed framework consistently improves rate--distortion performance across various bit-rate regions, e.g., 3.73% BD-rate gain over the state-of-the-art baseline on the Kodak dataset.