Download
Abstract

Recent years have seen a tremendous growth in both the capability and popularity of automatic machine analysis of images and video. As a result, a growing need for efficient compression methods optimized for machine vision, rather than human vision, has emerged. To meet this growing demand, several methods have been developed for image and video coding for machines. Unfortunately, while there is a substantial body of knowledge regarding rate-distortion theory for human vision, the same cannot be said of machine analysis. In this paper, we extend the current rate-distortion theory for machines, providing insight into important design considerations of machine-vision codecs. We then utilize this newfound understanding to improve several methods for learnable image coding for machines. Our proposed methods achieve state-of-the-art rate-distortion performance on several computer vision tasks such as classification, instance segmentation, and object detection.

Citation

Alon Harell, Yalda Foroutan, Nilesh A. Ahuja, Parual Datta, Bhavya Kanzariya, V. Srinivasa Somayazulu, Omesh Tickoo, Anderson de Andrade, & Ivan V. Bajic. (2025). “Rate-distortion theory in coding for machines and its applications.” IEEE TPAMI.

@article{DBLP:journals/pami/HarellFADKSTAB25,
  author       = {Alon Harell and
                  Yalda Foroutan and
                  Nilesh A. Ahuja and
                  Parual Datta and
                  Bhavya Kanzariya and
                  V. Srinivasa Somayazulu and
                  Omesh Tickoo and
                  Anderson de Andrade and
                  Ivan V. Bajic},
  title        = {Rate-Distortion Theory in Coding for Machines and Its Applications},
  journal      = {{IEEE TPAMI}},
  volume       = {47},
  number       = {7},
  pages        = {5501--5519},
  year         = {2025},
  url          = {https://doi.org/10.1109/TPAMI.2025.3548516},
  doi          = {10.1109/TPAMI.2025.3548516},
  timestamp    = {Sun, 06 Jul 2025 13:21:55 +0200},
  biburl       = {https://dblp.org/rec/journals/pami/HarellFADKSTAB25.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}