Flexible Variable-Rate Image Feature Compression for Edge-Cloud Systems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929298211864576 |
|---|---|
| author | Hossain, Md Adnan Faisal Duan, Zhihao Huang, Yuning Zhu, Fengqing |
| author_facet | Hossain, Md Adnan Faisal Duan, Zhihao Huang, Yuning Zhu, Fengqing |
| contents | Feature compression is a promising direction for coding for machines. Existing methods have made substantial progress, but they require designing and training separate neural network models to meet different specifications of compression rate, performance accuracy and computational complexity. In this paper, a flexible variable-rate feature compression method is presented that can operate on a range of rates by introducing a rate control parameter as an input to the neural network model. By compressing different intermediate features of a pre-trained vision task model, the proposed method can scale the encoding complexity without changing the overall size of the model. The proposed method is more flexible than existing baselines, at the same time outperforming them in terms of the three-way trade-off between feature compression rate, vision task accuracy, and encoding complexity. We have made the source code available at https://github.com/adnan-hossain/var_feat_comp.git. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_00432 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Flexible Variable-Rate Image Feature Compression for Edge-Cloud Systems Hossain, Md Adnan Faisal Duan, Zhihao Huang, Yuning Zhu, Fengqing Image and Video Processing Feature compression is a promising direction for coding for machines. Existing methods have made substantial progress, but they require designing and training separate neural network models to meet different specifications of compression rate, performance accuracy and computational complexity. In this paper, a flexible variable-rate feature compression method is presented that can operate on a range of rates by introducing a rate control parameter as an input to the neural network model. By compressing different intermediate features of a pre-trained vision task model, the proposed method can scale the encoding complexity without changing the overall size of the model. The proposed method is more flexible than existing baselines, at the same time outperforming them in terms of the three-way trade-off between feature compression rate, vision task accuracy, and encoding complexity. We have made the source code available at https://github.com/adnan-hossain/var_feat_comp.git. |
| title | Flexible Variable-Rate Image Feature Compression for Edge-Cloud Systems |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2404.00432 |