Training-Free Adaptive Quantization for Variable Rate Image Coding for Machines
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908746068787200 |
|---|---|
| author | Tatsumi, Yui Zeng, Ziyue Watanabe, Hiroshi |
| author_facet | Tatsumi, Yui Zeng, Ziyue Watanabe, Hiroshi |
| contents | Image Coding for Machines (ICM) has become increasingly important with the rapid integration of computer vision technology into real-world applications. However, most neural network-based ICM frameworks operate at a fixed rate, thus requiring individual training for each target bitrate. This limitation may restrict their practical usage. Existing variable rate image compression approaches mitigate this issue but often rely on additional training, which increases computational costs and complicates deployment. Moreover, variable rate control has not been thoroughly explored for ICM. To address these challenges, we propose a training-free framework for quantization strength control which enables flexible bitrate adjustment. By exploiting the scale parameter predicted by the hyperprior network, the proposed method adaptively modulates quantization step sizes across both channel and spatial dimensions. This allows the model to preserve semantically important regions while coarsely quantizing less critical areas. Our architectural design further enables continuous bitrate control through a single parameter. Experimental results demonstrate the effectiveness of our proposed method, achieving up to 11.07% BD-rate savings over the non-adaptive variable rate baseline. The code is available at https://github.com/qwert-top/AQVR-ICM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_05836 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Training-Free Adaptive Quantization for Variable Rate Image Coding for Machines Tatsumi, Yui Zeng, Ziyue Watanabe, Hiroshi Image and Video Processing Computer Vision and Pattern Recognition Image Coding for Machines (ICM) has become increasingly important with the rapid integration of computer vision technology into real-world applications. However, most neural network-based ICM frameworks operate at a fixed rate, thus requiring individual training for each target bitrate. This limitation may restrict their practical usage. Existing variable rate image compression approaches mitigate this issue but often rely on additional training, which increases computational costs and complicates deployment. Moreover, variable rate control has not been thoroughly explored for ICM. To address these challenges, we propose a training-free framework for quantization strength control which enables flexible bitrate adjustment. By exploiting the scale parameter predicted by the hyperprior network, the proposed method adaptively modulates quantization step sizes across both channel and spatial dimensions. This allows the model to preserve semantically important regions while coarsely quantizing less critical areas. Our architectural design further enables continuous bitrate control through a single parameter. Experimental results demonstrate the effectiveness of our proposed method, achieving up to 11.07% BD-rate savings over the non-adaptive variable rate baseline. The code is available at https://github.com/qwert-top/AQVR-ICM. |
| title | Training-Free Adaptive Quantization for Variable Rate Image Coding for Machines |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.05836 |