# Compressing Weight-updates for Image Artifacts Removal Neural Networks

arXiv: https://arxiv.org/abs/1905.04079 · HTML: https://mlsanity.com/paper/1905.04079/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 May 2019.

## Built on by (most cited first, 6 of 6)

- [Overfitting for Fun and Profit: Instance-Adaptive Data Compression](https://mlsanity.com/paper/2101.08687/) (2021)
- [Learned Image Coding for Machines: A Content-Adaptive Approach](https://mlsanity.com/paper/2108.09992/) (2021)
- [Instance-Adaptive Video Compression: Improving Neural Codecs by Training on the Test Set](https://mlsanity.com/paper/2111.10302/) (2021)
- [Universal Deep Image Compression via Content-Adaptive Optimization with Adapters](https://mlsanity.com/paper/2211.00918/) (2022)
- [Adaptation and Attention for Neural Video Coding](https://mlsanity.com/paper/2112.08767/) (2021)
- [Frequency-Aware Re-Parameterization for Over-Fitting Based Image Compression](https://mlsanity.com/paper/2310.08068/) (2023)

## Abstract (arXiv)

In this paper, we present a novel approach for fine-tuning a decoder-side neural network in the context of image compression, such that the weight-updates are better compressible. At encoder side, we fine-tune a pre-trained artifact removal network on target data by using a compression objective applied on the weight-update. In particular, the compression objective encourages weight-updates which are sparse and closer to quantized values. This way, the final weight-update can be compressed more efficiently by pruning and quantization, and can be included into the encoded bitstream together with the image bitstream of a traditional codec. We show that this approach achieves reconstruction quality which is on-par or slightly superior to a traditional codec, at comparable bitrates. To our knowledge, this is the first attempt to combine image compression and neural network's weight update compression.