# Machine Perception-Driven Image Compression: A Layered Generative Approach

arXiv: https://arxiv.org/abs/2304.06896 · HTML: https://mlsanity.com/paper/2304.06896/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 66 references that are in the map.
- First posted on arXiv 14 Apr 2023.

## Builds on (most cited first, 30 of 42)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [Multi-Task Learning as Multi-Objective Optimization](https://mlsanity.com/paper/1810.04650/) (2018)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [High-Fidelity Generative Image Compression](https://mlsanity.com/paper/2006.09965/) (2020)
- [DRIT++: Diverse Image-to-Image Translation via Disentangled Representations](https://mlsanity.com/paper/1905.01270/) (2019)
- [Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations](https://mlsanity.com/paper/1704.00648/) (2017)
- [Compressed Video Action Recognition](https://mlsanity.com/paper/1712.00636/) (2017)
- [Non-local Attention Optimized Deep Image Compression](https://mlsanity.com/paper/1904.09757/) (2019)
- [Image and Video Compression with Neural Networks: A Review](https://mlsanity.com/paper/1904.03567/) (2019)
- [Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics](https://mlsanity.com/paper/2001.03569/) (2020)
- [Learning Convolutional Networks for Content-weighted Image Compression](https://mlsanity.com/paper/1703.10553/) (2017)
- [Towards Image Understanding from Deep Compression without Decoding](https://mlsanity.com/paper/1803.06131/) (2018)
- [Deep Residual Learning in the JPEG Transform Domain](https://mlsanity.com/paper/1812.11690/) (2018)
- [Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach](https://mlsanity.com/paper/1706.00906/) (2017)
- [Towards Coding for Human and Machine Vision: A Scalable Image Coding Approach](https://mlsanity.com/paper/2001.02915/) (2020)
- [DSSLIC: Deep Semantic Segmentation-based Layered Image Compression](https://mlsanity.com/paper/1806.03348/) (2018)

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

- [Generative Visual Compression: A Review](https://mlsanity.com/paper/2402.02140/) (2024)
- [Switchable Token-Specific Codebook Quantization For Face Image Compression](https://mlsanity.com/paper/2510.22943/) (2025)
- [Learning on JPEG-LDPC Compressed Images: Classifying with Syndromes](https://mlsanity.com/paper/2403.10202/) (2024)
- [Hierarchical Semantic Compression for Consistent Image Semantic Restoration](https://mlsanity.com/paper/2502.16799/) (2025)
- [A Noise Constrained Diffusion (NC-Diffusion) Framework for High Fidelity Image Compression](https://mlsanity.com/paper/2604.06568/) (2026)
- [Goal-Oriented Source Coding using LDPC Codes for Compressed-Domain Image Classification](https://mlsanity.com/paper/2503.11954/) (2025)

## Abstract (arXiv)

In this age of information, images are a critical medium for storing and transmitting information. With the rapid growth of image data amount, visual compression and visual data perception are two important research topics attracting a lot attention. However, those two topics are rarely discussed together and follow separate research path. Due to the compact compressed domain representation offered by learning-based image compression methods, there exists possibility to have one stream targeting both efficient data storage and compression, and machine perception tasks. In this paper, we propose a layered generative image compression model achieving high human vision-oriented image reconstructed quality, even at extreme compression ratios. To obtain analysis efficiency and flexibility, a task-agnostic learning-based compression model is proposed, which effectively supports various compressed domain-based analytical tasks while reserves outstanding reconstructed perceptual quality, compared with traditional and learning-based codecs. In addition, joint optimization schedule is adopted to acquire best balance point among compression ratio, reconstructed image quality, and downstream perception performance. Experimental results verify that our proposed compressed domain-based multi-task analysis method can achieve comparable analysis results against the RGB image-based methods with up to 99.6% bit rate saving (i.e., compared with taking original RGB image as the analysis model input). The practical ability of our model is further justified from model size and information fidelity aspects.