Camera clustering for scalable stream-based active distillation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929315596206080 |
|---|---|
| author | Manjah, Dani Cacciarelli, Davide De Vleeschouwer, Christophe Macq, Benoit |
| author_facet | Manjah, Dani Cacciarelli, Davide De Vleeschouwer, Christophe Macq, Benoit |
| contents | We present a scalable framework designed to craft efficient lightweight models for video object detection utilizing self-training and knowledge distillation techniques. We scrutinize methodologies for the ideal selection of training images from video streams and the efficacy of model sharing across numerous cameras. By advocating for a camera clustering methodology, we aim to diminish the requisite number of models for training while augmenting the distillation dataset. The findings affirm that proper camera clustering notably amplifies the accuracy of distilled models, eclipsing the methodologies that employ distinct models for each camera or a universal model trained on the aggregate camera data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_10411 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Camera clustering for scalable stream-based active distillation Manjah, Dani Cacciarelli, Davide De Vleeschouwer, Christophe Macq, Benoit Computer Vision and Pattern Recognition We present a scalable framework designed to craft efficient lightweight models for video object detection utilizing self-training and knowledge distillation techniques. We scrutinize methodologies for the ideal selection of training images from video streams and the efficacy of model sharing across numerous cameras. By advocating for a camera clustering methodology, we aim to diminish the requisite number of models for training while augmenting the distillation dataset. The findings affirm that proper camera clustering notably amplifies the accuracy of distilled models, eclipsing the methodologies that employ distinct models for each camera or a universal model trained on the aggregate camera data. |
| title | Camera clustering for scalable stream-based active distillation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.10411 |