# Universal Representations for Classification-enhanced Lossy Compression

arXiv: https://arxiv.org/abs/2504.13191 · HTML: https://mlsanity.com/paper/2504.13191/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 19 references that are in the map.
- First posted on arXiv 12 Apr 2025.

## Builds on (most cited first, 11 of 11)

- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [High-Fidelity Generative Image Compression](https://mlsanity.com/paper/2006.09965/) (2020)
- [Generative Adversarial Networks for Extreme Learned Image Compression](https://mlsanity.com/paper/1804.02958/) (2018)
- [Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff](https://mlsanity.com/paper/1901.07821/) (2019)
- [Conditional Probability Models for Deep Image Compression](https://mlsanity.com/paper/1801.04260/) (2018)
- [Recent Advances in Autoencoder-Based Representation Learning](https://mlsanity.com/paper/1812.05069/) (2018)
- [A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses](https://mlsanity.com/paper/2003.08983/) (2020)
- [Deep Generative Models for Distribution-Preserving Lossy Compression](https://mlsanity.com/paper/1805.11057/) (2018)
- [Universal Rate-Distortion-Perception Representations for Lossy Compression](https://mlsanity.com/paper/2106.10311/) (2021)
- [On the advantages of stochastic encoders](https://mlsanity.com/paper/2102.09270/) (2021)
- [On The Classification-Distortion-Perception Tradeoff](https://mlsanity.com/paper/1904.08816/) (2019)

## Abstract (arXiv)

In lossy compression, the classical tradeoff between compression rate and reconstruction distortion has traditionally guided algorithm design. However, Blau and Michaeli [5] introduced a generalized framework, known as the rate-distortion-perception (RDP) function, incorporating perceptual quality as an additional dimension of evaluation. More recently, the rate-distortion-classification (RDC) function was investigated in [19], evaluating compression performance by considering classification accuracy alongside distortion. In this paper, we explore universal representations, where a single encoder is developed to achieve multiple decoding objectives across various distortion and classification (or perception) constraints. This universality avoids retraining encoders for each specific operating point within these tradeoffs. Our experimental validation on the MNIST dataset indicates that a universal encoder incurs only minimal performance degradation compared to individually optimized encoders for perceptual image compression tasks, aligning with prior results from [23]. Nonetheless, we also identify that in the RDC setting, reusing an encoder optimized for one specific classification-distortion tradeoff leads to a significant distortion penalty when applied to alternative points.