# A Compression Objective and a Cycle Loss for Neural Image Compression

arXiv: https://arxiv.org/abs/1905.10371 · HTML: https://mlsanity.com/paper/1905.10371/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2019.

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

- [Instance-Adaptive Video Compression: Improving Neural Codecs by Training on the Test Set](https://mlsanity.com/paper/2111.10302/) (2021)
- [Adaptation and Attention for Neural Video Coding](https://mlsanity.com/paper/2112.08767/) (2021)
- [Compositional Adversarial Training for Robust Visual Watermarking](https://mlsanity.com/paper/2605.16720/) (2026)

## Abstract (arXiv)

In this manuscript we propose two objective terms for neural image compression: a compression objective and a cycle loss. These terms are applied on the encoder output of an autoencoder and are used in combination with reconstruction losses. The compression objective encourages sparsity and low entropy in the activations. The cycle loss term represents the distortion between encoder outputs computed from the original image and from the reconstructed image (code-domain distortion). We train different autoencoders by using the compression objective in combination with different losses: a) MSE, b) MSE and MSSSIM, c) MSE, MS-SSIM and cycle loss. We observe that images encoded by these differently-trained autoencoders fall into different points of the perception-distortion curve (while having similar bit-rates). In particular, MSE-only training favors low image-domain distortion, whereas cycle loss training favors high perceptual quality.