Progressive Learned Image Compression for Machine Perception
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908730245775360 |
|---|---|
| author | Kim, Jungwoo Kim, Jun-Hyuk Lee, Jong-Seok |
| author_facet | Kim, Jungwoo Kim, Jun-Hyuk Lee, Jong-Seok |
| contents | Recent advances in learned image codecs have been extended from human perception toward machine perception. However, progressive image compression with fine granular scalability (FGS)-which enables decoding a single bitstream at multiple quality levels-remains unexplored for machine-oriented codecs. In this work, we propose a novel progressive learned image compression codec for machine perception, PICM-Net, based on trit-plane coding. By analyzing the difference between human- and machine-oriented rate-distortion priorities, we systematically examine the latent prioritization strategies in terms of machine-oriented codecs. To further enhance real-world adaptability, we design an adaptive decoding controller, which dynamically determines the necessary decoding level during inference time to maintain the desired confidence of downstream machine prediction. Extensive experiments demonstrate that our approach enables efficient and adaptive progressive transmission while maintaining high performance in the downstream classification task, establishing a new paradigm for machine-aware progressive image compression. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_20070 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Progressive Learned Image Compression for Machine Perception Kim, Jungwoo Kim, Jun-Hyuk Lee, Jong-Seok Computer Vision and Pattern Recognition Image and Video Processing Recent advances in learned image codecs have been extended from human perception toward machine perception. However, progressive image compression with fine granular scalability (FGS)-which enables decoding a single bitstream at multiple quality levels-remains unexplored for machine-oriented codecs. In this work, we propose a novel progressive learned image compression codec for machine perception, PICM-Net, based on trit-plane coding. By analyzing the difference between human- and machine-oriented rate-distortion priorities, we systematically examine the latent prioritization strategies in terms of machine-oriented codecs. To further enhance real-world adaptability, we design an adaptive decoding controller, which dynamically determines the necessary decoding level during inference time to maintain the desired confidence of downstream machine prediction. Extensive experiments demonstrate that our approach enables efficient and adaptive progressive transmission while maintaining high performance in the downstream classification task, establishing a new paradigm for machine-aware progressive image compression. |
| title | Progressive Learned Image Compression for Machine Perception |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2512.20070 |