# Substitutional Neural Image Compression

arXiv: https://arxiv.org/abs/2105.07512 · HTML: https://mlsanity.com/paper/2105.07512/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 37 references that are in the map.
- First posted on arXiv 16 May 2021.

## Builds on (most cited first, 16 of 16)

- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [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)
- [Generative Adversarial Networks for Extreme Learned Image Compression](https://mlsanity.com/paper/1804.02958/) (2018)
- [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)
- [Conditional Probability Models for Deep Image Compression](https://mlsanity.com/paper/1801.04260/) (2018)
- [Real-Time Adaptive Image Compression](https://mlsanity.com/paper/1705.05823/) (2017)
- [Variable Rate Deep Image Compression With a Conditional Autoencoder](https://mlsanity.com/paper/1909.04802/) (2019)
- [Generative Compression](https://mlsanity.com/paper/1703.01467/) (2017)
- [Content Adaptive Optimization for Neural Image Compression](https://mlsanity.com/paper/1906.01223/) (2019)
- [Variable Rate Deep Image Compression with Modulated Autoencoder](https://mlsanity.com/paper/1912.05526/) (2019)
- [Block-optimized Variable Bit Rate Neural Image Compression](https://mlsanity.com/paper/1805.10887/) (2018)
- [Lossy Compression with Distortion Constrained Optimization](https://mlsanity.com/paper/2005.04064/) (2020)

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

- [Content Adaptive Latents and Decoder for Neural Image Compression](https://mlsanity.com/paper/2212.10132/) (2022)
- [Online Meta Adaptation for Variable-Rate Learned Image Compression](https://mlsanity.com/paper/2111.08256/) (2021)
- [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)

## Abstract (arXiv)

We describe Substitutional Neural Image Compression (SNIC), a general approach for enhancing any neural image compression model, that requires no data or additional tuning of the trained model. It boosts compression performance toward a flexible distortion metric and enables bit-rate control using a single model instance. The key idea is to replace the image to be compressed with a substitutional one that outperforms the original one in a desired way. Finding such a substitute is inherently difficult for conventional codecs, yet surprisingly favorable for neural compression models thanks to their fully differentiable structures. With gradients of a particular loss backpropogated to the input, a desired substitute can be efficiently crafted iteratively. We demonstrate the effectiveness of SNIC, when combined with various neural compression models and target metrics, in improving compression quality and performing bit-rate control measured by rate-distortion curves. Empirical results of control precision and generation speed are also discussed.