Compressive Feature Selection for Remote Visual Multi-Task Inference
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916247164157952 |
|---|---|
| author | Alvar, Saeed Ranjbar Bajić, Ivan V. |
| author_facet | Alvar, Saeed Ranjbar Bajić, Ivan V. |
| contents | Deep models produce a number of features in each internal layer. A key problem in applications such as feature compression for remote inference is determining how important each feature is for the task(s) performed by the model. The problem is especially challenging in the case of multi-task inference, where the same feature may carry different importance for different tasks. In this paper, we examine how effective is mutual information (MI) between a feature and a model's task output as a measure of the feature's importance for that task. Experiments involving hard selection and soft selection (unequal compression) based on MI are carried out to compare the MI-based method with alternative approaches. Multi-objective analysis is provided to offer further insight. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_09077 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Compressive Feature Selection for Remote Visual Multi-Task Inference Alvar, Saeed Ranjbar Bajić, Ivan V. Image and Video Processing Computer Vision and Pattern Recognition Deep models produce a number of features in each internal layer. A key problem in applications such as feature compression for remote inference is determining how important each feature is for the task(s) performed by the model. The problem is especially challenging in the case of multi-task inference, where the same feature may carry different importance for different tasks. In this paper, we examine how effective is mutual information (MI) between a feature and a model's task output as a measure of the feature's importance for that task. Experiments involving hard selection and soft selection (unequal compression) based on MI are carried out to compare the MI-based method with alternative approaches. Multi-objective analysis is provided to offer further insight. |
| title | Compressive Feature Selection for Remote Visual Multi-Task Inference |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.09077 |