# Memory-Efficient Learned Image Compression with Pruned Hyperprior Module

arXiv: https://arxiv.org/abs/2206.10083 · HTML: https://mlsanity.com/paper/2206.10083/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jun 2022.

## Built on by (most cited first, 7 of 7)

- [Learned Image Compression with Mixed Transformer-CNN Architectures](https://mlsanity.com/paper/2303.14978/) (2023)
- [Neural Image Compression: Generalization, Robustness, and Spectral Biases](https://mlsanity.com/paper/2307.08657/) (2023)
- [Accelerating Learnt Video Codecs with Gradient Decay and Layer-wise Distillation](https://mlsanity.com/paper/2312.02605/) (2023)
- [Survey on Visual Signal Coding and Processing with Generative Models: Technologies, Standards and Optimization](https://mlsanity.com/paper/2405.14221/) (2024)
- [Structured Pruning and Quantization for Learned Image Compression](https://mlsanity.com/paper/2506.01229/) (2025)
- [DynaQuant: Dynamic Mixed-Precision Quantization for Learned Image Compression](https://mlsanity.com/paper/2511.07903/) (2025)
- [REMAC: Reference-Based Martian Asymmetrical Image Compression](https://mlsanity.com/paper/2601.18547/) (2026)

## Abstract (arXiv)

Learned Image Compression (LIC) gradually became more and more famous in these years. The hyperprior-module-based LIC models have achieved remarkable rate-distortion performance. However, the memory cost of these LIC models is too large to actually apply them to various devices, especially to portable or edge devices. The parameter scale is directly linked with memory cost. In our research, we found the hyperprior module is not only highly over-parameterized, but also its latent representation contains redundant information. Therefore, we propose a novel pruning method named ERHP in this paper to efficiently reduce the memory cost of hyperprior module, while improving the network performance. The experiments show our method is effective, reducing at least 22.6% parameters in the whole model while achieving better rate-distortion performance.