# You've Seen Enough: Quality-Constrained Image Coding for Machines

arXiv: https://arxiv.org/abs/2609.25108 · HTML: https://mlsanity.com/paper/2609.25108/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 35 references that are in the map.
- First posted on arXiv 20 Sep 2026.

## Builds on (most cited first, 27 of 27)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding](https://mlsanity.com/paper/2203.10886/) (2022)
- [CompressAI: a PyTorch library and evaluation platform for end-to-end compression research](https://mlsanity.com/paper/2011.03029/) (2020)
- [Checkerboard Context Model for Efficient Learned Image Compression](https://mlsanity.com/paper/2103.15306/) (2021)
- [Variable Rate Image Compression with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06085/) (2015)
- [Lossy Image Compression with Conditional Diffusion Models](https://mlsanity.com/paper/2209.06950/) (2022)
- [Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics](https://mlsanity.com/paper/2001.03569/) (2020)
- [Scalable Image Coding for Humans and Machines](https://mlsanity.com/paper/2107.08373/) (2021)
- [Image coding for machines: an end-to-end learned approach](https://mlsanity.com/paper/2108.09993/) (2021)
- [PO-ELIC: Perception-Oriented Efficient Learned Image Coding](https://mlsanity.com/paper/2205.14501/) (2022)
- [Image Coding for Machines with Omnipotent Feature Learning](https://mlsanity.com/paper/2207.01932/) (2022)
- [Learned Image Coding for Machines: A Content-Adaptive Approach](https://mlsanity.com/paper/2108.09992/) (2021)
- [Preprocessing Enhanced Image Compression for Machine Vision](https://mlsanity.com/paper/2206.05650/) (2022)
- [Image Coding for Machines with Edge Information Learning Using Segment Anything](https://mlsanity.com/paper/2403.04173/) (2024)
- [Recent Standard Development Activities on Video Coding for Machines](https://mlsanity.com/paper/2105.12653/) (2021)
- [Efficient Contextformer: Spatio-Channel Window Attention for Fast Context Modeling in Learned Image Compression](https://mlsanity.com/paper/2306.14287/) (2023)
- [Generalized Gaussian Model for Learned Image Compression](https://mlsanity.com/paper/2411.19320/) (2024)
- [Lossy Compression with Distortion Constrained Optimization](https://mlsanity.com/paper/2005.04064/) (2020)
- [Efficient Feature Compression for Edge-Cloud Systems](https://mlsanity.com/paper/2211.09897/) (2022)
- [Channel-wise Feature Decorrelation for Enhanced Learned Image Compression](https://mlsanity.com/paper/2403.10936/) (2024)
- [Emerging Standards for Machine-to-Machine Video Coding](https://mlsanity.com/paper/2512.10230/) (2025)
- [CompressAI-Vision: Open-source software to evaluate compression methods for computer vision tasks](https://mlsanity.com/paper/2509.20777/) (2025)

## Abstract (arXiv)

Visual data is increasingly consumed by machine-vision systems rather than by human observers. Image Coding for Machines (ICM) compresses images assuming the main observer is a computer vision application and that the human observer needs to inspect or validate the decisions. Inspired by just-noticeable distortion, we cap human-observed quality at a desired level and devote the remaining bits to machine performance. Specifically, joint compression-segmentation training is recast as a constrained optimization problem in which the codec must meet a predefined acceptable target visual quality while a task term consumes the remaining coding capacity. This paper proposes two variants of a penalty function that guides the quality toward the target: an absolute function and a bilinear function, the latter applying a steeper slope once the target visual quality is exceeded. Experimental results show that, under the quality constraint, the proposed method achieves BD-rates of -22.82% and -29.81% relative to an unconstrained joint rate--distortion--task optimization and a simple rate--distortion baseline, respectively, showcasing bitrate reduction with the same task performance. This is achieved while the codec also meets the target visual quality with a reasonable error and without adding any complexity overhead.