Rate-Distortion Theory in Coding for Machines and its Application
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929739758829568 |
|---|---|
| author | Harell, Alon Foroutan, Yalda Ahuja, Nilesh Datta, Parual Kanzariya, Bhavya Somayazulu, V. Srinivasa Tickoo, Omesh de Andrade, Anderson Bajic, Ivan V. |
| author_facet | Harell, Alon Foroutan, Yalda Ahuja, Nilesh Datta, Parual Kanzariya, Bhavya Somayazulu, V. Srinivasa Tickoo, Omesh de Andrade, Anderson Bajic, Ivan V. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_17295 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Rate-Distortion Theory in Coding for Machines and its Application Harell, Alon Foroutan, Yalda Ahuja, Nilesh Datta, Parual Kanzariya, Bhavya Somayazulu, V. Srinivasa Tickoo, Omesh de Andrade, Anderson Bajic, Ivan V. Image and Video Processing Information Theory 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. |
| title | Rate-Distortion Theory in Coding for Machines and its Application |
| topic | Image and Video Processing Information Theory |
| url | https://arxiv.org/abs/2305.17295 |