# Scalable Facial Image Compression with Deep Feature Reconstruction

arXiv: https://arxiv.org/abs/1903.05921 · HTML: https://mlsanity.com/paper/1903.05921/

## Key facts

- Cited by 8 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 14 Mar 2019.

## Built on by (most cited first, 8 of 8)

- [A Coding Framework and Benchmark towards Low-Bitrate Video Understanding](https://mlsanity.com/paper/2202.02813/) (2022)
- [An Equivalence Between Data Poisoning and Byzantine Gradient Attacks](https://mlsanity.com/paper/2202.08578/) (2022)
- [Video Coding for Machine: Compact Visual Representation Compression for Intelligent Collaborative Analytics](https://mlsanity.com/paper/2110.09241/) (2021)
- [Perceptual Video Coding for Machines via Satisfied Machine Ratio Modeling](https://mlsanity.com/paper/2211.06797/) (2022)
- [Identity Preserving Loss for Learned Image Compression](https://mlsanity.com/paper/2204.10869/) (2022)
- [FaSDiff: Balancing Perception and Semantics in Face Compression via Stable Diffusion Priors](https://mlsanity.com/paper/2505.05870/) (2025)
- [Optimized Learned Image Compression for Facial Expression Recognition](https://mlsanity.com/paper/2509.17262/) (2025)
- [Visual Token Codec: Unleashing Spatial Redundancy for ViT Feature Coding](https://mlsanity.com/paper/2608.08832/) (2026)

## Abstract (arXiv)

In this paper, we propose a scalable image compression scheme, including the base layer for feature representation and enhancement layer for texture representation. More specifically, the base layer is designed as the deep learning feature for analysis purpose, and it can also be converted to the fine structure with deep feature reconstruction. The enhancement layer, which serves to compress the residuals between the input image and the signals generated from the base layer, aims to faithfully reconstruct the input texture. The proposed scheme can feasibly inherit the advantages of both compress-then-analyze and analyze-then-compress schemes in surveillance applications. The performance of this framework is validated with facial images, and the conducted experiments provide useful evidences to show that the proposed framework can achieve better rate-accuracy and rate-distortion performance over conventional image compression schemes.