# Learned Compression of Encoding Distributions

arXiv: https://arxiv.org/abs/2406.13059 · HTML: https://mlsanity.com/paper/2406.13059/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 23 references that are in the map.
- First posted on arXiv 18 Jun 2024.

## Builds on (most cited first, 18 of 18)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [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)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [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)
- [Lossy Image Compression with Compressive Autoencoders](https://mlsanity.com/paper/1703.00395/) (2017)
- [CompressAI: a PyTorch library and evaluation platform for end-to-end compression research](https://mlsanity.com/paper/2011.03029/) (2020)
- [Inference Suboptimality in Variational Autoencoders](https://mlsanity.com/paper/1801.03558/) (2018)
- [Asymmetric Gained Deep Image Compression With Continuous Rate Adaptation](https://mlsanity.com/paper/2003.02012/) (2020)
- [Content Adaptive Optimization for Neural Image Compression](https://mlsanity.com/paper/1906.01223/) (2019)
- [Overfitting for Fun and Profit: Instance-Adaptive Data Compression](https://mlsanity.com/paper/2101.08687/) (2021)
- [QVRF: A Quantization-error-aware Variable Rate Framework for Learned Image Compression](https://mlsanity.com/paper/2303.05744/) (2023)
- [Reducing The Amortization Gap of Entropy Bottleneck In End-to-End Image Compression](https://mlsanity.com/paper/2209.00964/) (2022)
- [Entropy Coding Improvement for Low-complexity Compressive Auto-encoders](https://mlsanity.com/paper/2303.05962/) (2023)

## Built on by (most cited first, 1 of 1)

- [Test-time adaptation for image compression with distribution regularization](https://mlsanity.com/paper/2410.12191/) (2024)

## Abstract (arXiv)

The entropy bottleneck introduced by Ball'e et al. is a common component used in many learned compression models. It encodes a transformed latent representation using a static distribution whose parameters are learned during training. However, the actual distribution of the latent data may vary wildly across different inputs. The static distribution attempts to encompass all possible input distributions, thus fitting none of them particularly well. This unfortunate phenomenon, sometimes known as the amortization gap, results in suboptimal compression. To address this issue, we propose a method that dynamically adapts the encoding distribution to match the latent data distribution for a specific input. First, our model estimates a better encoding distribution for a given input. This distribution is then compressed and transmitted as an additional side-information bitstream. Finally, the decoder reconstructs the encoding distribution and uses it to decompress the corresponding latent data. Our method achieves a Bjontegaard-Delta (BD)-rate gain of -7.10% on the Kodak test dataset when applied to the standard fully-factorized architecture. Furthermore, considering computational complexity, the transform used by our method is an order of magnitude cheaper in terms of Multiply-Accumulate (MAC) operations compared to related side-information methods such as the scale hyperprior.