analiza aiqbench
This research introduces Image Coding for Machines (ICM), a framework that optimizes image compression by prioritizing computer vision task performance while strictly capping visual quality at a level acceptable to human inspectors. By treating the constraint on human-observable distortion as a boundary condition, the method reallocates coding capacity to enhance machine accuracy, achieving significant bitrate reductions without increasing computational complexity. The approach effectively bridges the gap between human validation requirements and machine utility, offering a practical solution for deploying efficient vision systems in regulated or hybrid environments.
You've Seen Enough: Quality-Constrained Image Coding for Machines
arXiv:2609.25108v1 Announce Type: cross Abstract: 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, which sets the quality to the just-acceptable level for human observers, we aim to cap the human-observed quality at a desired level, with the goal of using the remaining coding capacity to improve the machine performance. We recast joint compression-segmentation training 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. We solve this by designing a penalty function to guide the quality to the desired target. We propose two penalty functions, 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 a BD-rate of $-22.82\%$ over an unconstrained joint rate--distortion--task optimization and $-29.81\%$ over a simple rate--distortion baseline, 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.
Abstract: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, which sets the quality to the just-acceptable level for human observers, we aim to cap the human-observed quality at a desired level, with the goal of using the remaining coding capacity to improve the machine performance. We recast joint compression-segmentation training 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. We solve this by designing a penalty function to guide the quality to the desired target. We propose two penalty functions, 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 a BD-rate of $-22.82\%$ over an unconstrained joint rate--distortion--task optimization and $-29.81\%$ over a simple rate--distortion baseline, 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.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2609.25108 [cs.CV]
(or arXiv:2609.25108v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2609.25108 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 310 cuvinte
Subiecte conexe
[AINews] Opus 5.5 is good at explainer videos
Latent Space · 29 sept. 2026
[AINews] The Future of Latent Space
Latent Space · 25 sept. 2026
Lattice-Based Cryptography Explained
Quantum Zeitgeist · 15 aug. 2026
Humanity’s Last Invention — Richard Socher of Recursive
Latent Space · 14 sept. 2026