Data-Efficient Stream-Based Active Distillation for Scalable Edge Model Deployment
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915511742234624 |
|---|---|
| author | Manjah, Dani Bary, Tim Gérin, Benoît Macq, Benoît de Vleeschouwer, Christophe |
| author_facet | Manjah, Dani Bary, Tim Gérin, Benoît Macq, Benoît de Vleeschouwer, Christophe |
| contents | Edge camera-based systems are continuously expanding, facing ever-evolving environments that require regular model updates. In practice, complex teacher models are run on a central server to annotate data, which is then used to train smaller models tailored to the edge devices with limited computational power. This work explores how to select the most useful images for training to maximize model quality while keeping transmission costs low. Our work shows that, for a similar training load (i.e., iterations), a high-confidence stream-based strategy coupled with a diversity-based approach produces a high-quality model with minimal dataset queries. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_20484 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Data-Efficient Stream-Based Active Distillation for Scalable Edge Model Deployment Manjah, Dani Bary, Tim Gérin, Benoît Macq, Benoît de Vleeschouwer, Christophe Computer Vision and Pattern Recognition Edge camera-based systems are continuously expanding, facing ever-evolving environments that require regular model updates. In practice, complex teacher models are run on a central server to annotate data, which is then used to train smaller models tailored to the edge devices with limited computational power. This work explores how to select the most useful images for training to maximize model quality while keeping transmission costs low. Our work shows that, for a similar training load (i.e., iterations), a high-confidence stream-based strategy coupled with a diversity-based approach produces a high-quality model with minimal dataset queries. |
| title | Data-Efficient Stream-Based Active Distillation for Scalable Edge Model Deployment |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.20484 |