# Online Meta Adaptation for Variable-Rate Learned Image Compression

arXiv: https://arxiv.org/abs/2111.08256 · HTML: https://mlsanity.com/paper/2111.08256/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 16 Nov 2021.

## Builds on (most cited first, 26 of 26)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (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)
- [How to train your MAML](https://mlsanity.com/paper/1810.09502/) (2018)
- [Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning](https://mlsanity.com/paper/1803.11347/) (2018)
- [CompressAI: a PyTorch library and evaluation platform for end-to-end compression research](https://mlsanity.com/paper/2011.03029/) (2020)
- [Checkerboard Context Model for Efficient Learned Image Compression](https://mlsanity.com/paper/2103.15306/) (2021)
- [Full Resolution Image Compression with Recurrent Neural Networks](https://mlsanity.com/paper/1608.05148/) (2016)
- [Variable Rate Image Compression with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06085/) (2015)
- [Context-adaptive Entropy Model for End-to-end Optimized Image Compression](https://mlsanity.com/paper/1809.10452/) (2018)
- [Online Meta-Learning](https://mlsanity.com/paper/1902.08438/) (2019)
- [Conditional Probability Models for Deep Image Compression](https://mlsanity.com/paper/1801.04260/) (2018)
- [Meta-Transfer Learning for Zero-Shot Super-Resolution](https://mlsanity.com/paper/2002.12213/) (2020)
- [Variable Rate Deep Image Compression With a Conditional Autoencoder](https://mlsanity.com/paper/1909.04802/) (2019)
- [Online Deep Learning: Learning Deep Neural Networks on the Fly](https://mlsanity.com/paper/1711.03705/) (2017)
- [Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL](https://mlsanity.com/paper/1812.07671/) (2018)
- [Universally Quantized Neural Compression](https://mlsanity.com/paper/2006.09952/) (2020)
- [Soft then Hard: Rethinking the Quantization in Neural Image Compression](https://mlsanity.com/paper/2104.05168/) (2021)
- [Streaming Variational Bayes](https://mlsanity.com/paper/1307.6769/) (2013)
- [Variable Rate Deep Image Compression with Modulated Autoencoder](https://mlsanity.com/paper/1912.05526/) (2019)
- [Learned Multi-Resolution Variable-Rate Image Compression with Octave-based Residual Blocks](https://mlsanity.com/paper/2012.15463/) (2020)
- [3-D Context Entropy Model for Improved Practical Image Compression](https://mlsanity.com/paper/2004.08273/) (2020)
- [MetaHDR: Model-Agnostic Meta-Learning for HDR Image Reconstruction](https://mlsanity.com/paper/2103.12545/) (2021)
- [Substitutional Neural Image Compression](https://mlsanity.com/paper/2105.07512/) (2021)

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

- [Wavelet-Like Transform-Based Technology in Response to the Call for Proposals on Neural Network-Based Image Coding](https://mlsanity.com/paper/2403.05937/) (2024)
- [Rethinking Learned Image Compression: Context is All You Need](https://mlsanity.com/paper/2407.11590/) (2024)
- [A Secure and Efficient Multi-Object Grasping Detection Approach for Robotic Arms](https://mlsanity.com/paper/2209.03511/) (2022)

## Abstract (arXiv)

This work addresses two major issues of end-to-end learned image compression (LIC) based on deep neural networks: variable-rate learning where separate networks are required to generate compressed images with varying qualities, and the train-test mismatch between differentiable approximate quantization and true hard quantization. We introduce an online meta-learning (OML) setting for LIC, which combines ideas from meta learning and online learning in the conditional variational auto-encoder (CVAE) framework. By treating the conditional variables as meta parameters and treating the generated conditional features as meta priors, the desired reconstruction can be controlled by the meta parameters to accommodate compression with variable qualities. The online learning framework is used to update the meta parameters so that the conditional reconstruction is adaptively tuned for the current image. Through the OML mechanism, the meta parameters can be effectively updated through SGD. The conditional reconstruction is directly based on the quantized latent representation in the decoder network, and therefore helps to bridge the gap between the training estimation and true quantized latent distribution. Experiments demonstrate that our OML approach can be flexibly applied to different state-of-the-art LIC methods to achieve additional performance improvements with little computation and transmission overhead.