# The Rate-Distortion-Accuracy Tradeoff: JPEG Case Study

arXiv: https://arxiv.org/abs/2008.00605 · HTML: https://mlsanity.com/paper/2008.00605/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Aug 2020.

## Built on by (most cited first, 22 of 22)

- [An Introduction to Neural Data Compression](https://mlsanity.com/paper/2202.06533/) (2022)
- [Learning to Resize Images for Computer Vision Tasks](https://mlsanity.com/paper/2103.09950/) (2021)
- [Towards End-to-End Image Compression and Analysis with Transformers](https://mlsanity.com/paper/2112.09300/) (2021)
- [LVAC: Learned Volumetric Attribute Compression for Point Clouds using Coordinate Based Networks](https://mlsanity.com/paper/2111.08988/) (2021)
- [Differentiable JPEG: The Devil is in the Details](https://mlsanity.com/paper/2309.06978/) (2023)
- [FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computing](https://mlsanity.com/paper/2302.10681/) (2023)
- [Deep Perceptual Image Quality Assessment for Compression](https://mlsanity.com/paper/2103.01114/) (2021)
- [End-to-end optimized image compression for multiple machine tasks](https://mlsanity.com/paper/2103.04178/) (2021)
- [High-Perceptual Quality JPEG Decoding via Posterior Sampling](https://mlsanity.com/paper/2211.11827/) (2022)
- [High Efficiency Image Compression for Large Visual-Language Models](https://mlsanity.com/paper/2407.17060/) (2024)
- [A Robust Document Image Watermarking Scheme using Deep Neural Network](https://mlsanity.com/paper/2202.13067/) (2022)
- [Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Prior](https://mlsanity.com/paper/2511.22549/) (2025)
- [Differentiable bit-rate estimation for neural-based video codec enhancement](https://mlsanity.com/paper/2301.09776/) (2023)
- [JPEG Inspired Deep Learning](https://mlsanity.com/paper/2410.07081/) (2024)
- [An Adaptive Plug-and-Play Network for Few-Shot Learning](https://mlsanity.com/paper/2302.09326/) (2023)
- [Deep Video Codec Control for Vision Models](https://mlsanity.com/paper/2308.16215/) (2023)
- [A Perspective on Deep Vision Performance with Standard Image and Video Codecs](https://mlsanity.com/paper/2404.12330/) (2024)
- [Image Coding for Machines via Feature-Preserving Rate-Distortion Optimization](https://mlsanity.com/paper/2504.02216/) (2025)
- [TACTIC: Joint Rate-Distortion-Accuracy Optimisation for Low Bitrate Compression](https://mlsanity.com/paper/2109.10658/) (2021)
- [JPEG Compliant Compression for Both Human and Machine, A Report](https://mlsanity.com/paper/2503.10912/) (2025)
- [RDD: Pareto Analysis of the Rate-Distortion-Distinguishability Trade-off](https://mlsanity.com/paper/2509.24805/) (2025)
- [PIC: Revisiting INR for Image Coding with Fast Encoding and Sub-Millisecond Decoding](https://mlsanity.com/paper/2609.09020/) (2026)

## Abstract (arXiv)

Handling digital images is almost always accompanied by a lossy compression in order to facilitate efficient transmission and storage. This introduces an unavoidable tension between the allocated bit-budget (rate) and the faithfulness of the resulting image to the original one (distortion). An additional complicating consideration is the effect of the compression on recognition performance by given classifiers (accuracy). This work aims to explore this rate-distortion-accuracy tradeoff. As a case study, we focus on the design of the quantization tables in the JPEG compression standard. We offer a novel optimal tuning of these tables via continuous optimization, leveraging a differential implementation of both the JPEG encoder-decoder and an entropy estimator. This enables us to offer a unified framework that considers the interplay between rate, distortion and classification accuracy. In all these fronts, we report a substantial boost in performance by a simple and easily implemented modification of these tables.