# JPEG Compliant Compression for Both Human and Machine, A Report

arXiv: https://arxiv.org/abs/2503.10912 · HTML: https://mlsanity.com/paper/2503.10912/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 36 references that are in the map.
- First posted on arXiv 13 Mar 2025.

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

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information](https://mlsanity.com/paper/2401.08732/) (2024)
- [DeepN-JPEG: A Deep Neural Network Favorable JPEG-based Image Compression Framework](https://mlsanity.com/paper/1803.05788/) (2018)
- [The Rate-Distortion-Accuracy Tradeoff: JPEG Case Study](https://mlsanity.com/paper/2008.00605/) (2020)
- [Conditional Mutual Information Constrained Deep Learning for Classification](https://mlsanity.com/paper/2309.09123/) (2023)
- [Optimizing JPEG Quantization for Classification Networks](https://mlsanity.com/paper/2003.02874/) (2020)
- [Lost in Compression: the Impact of Lossy Image Compression on Variable Size Object Detection within Infrared Imagery](https://mlsanity.com/paper/2205.08002/) (2022)
- [AdaCompress: Adaptive Compression for Online Computer Vision Services](https://mlsanity.com/paper/1909.08148/) (2019)
- [Coded Deep Learning: Framework and Algorithm](https://mlsanity.com/paper/2501.09849/) (2025)

## Abstract (arXiv)

Deep Neural Networks (DNNs) have become an integral part of our daily lives, especially in vision-related applications. However, the conventional lossy image compression algorithms are primarily designed for the Human Vision System (HVS), which can non-trivially compromise the DNNs' validation accuracy after compression, as noted in citeliu2018deepn. Thus developing an image compression algorithm for both human and machine (DNNs) is on the horizon. To address the challenge mentioned above, in this paper, we first formulate the image compression as a multi-objective optimization problem which take both human and machine prespectives into account, then we solve it by linear combination, and proposed a novel distortion measure for both human and machine, dubbed Human and Machine-Oriented Error (HMOE). After that, we develop Human And Machine Oriented Soft Decision Quantization (HMOSDQ) based on HMOE, a lossy image compression algorithm for both human and machine (DNNs), and fully complied with JPEG format. In order to evaluate the performance of HMOSDQ, finally we conduct the experiments for two pre-trained well-known DNN-based image classifiers named Alexnet citeAlexnet and VGG-16 citesimonyan2014VGG on two subsets of the ImageNet citedeng2009imagenet validation set: one subset included images with shorter side in the range of 496 to 512, while the other included images with shorter side in the range of 376 to 384. Our results demonstrate that HMOSDQ outperforms the default JPEG algorithm in terms of rate-accuracy and rate-distortion performance. For the Alexnet comparing with the default JPEG algorithm, HMOSDQ can improve the validation accuracy by more than 0.81% at 0.61 BPP, or equivalently reduce the compression rate of default JPEG by 9.6× while maintaining the same validation accuracy.