Metraipolis › archive › dc_c82e35eb4f5b
Multi-Node Transformers for Object Detection and Captioning Across Distributed Edge Networks — arXiv:2611.11291
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.11291
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:45:44.037Z
- SHA-256 of the archived text
83cd0d3c122293a48bed8e71829d041ec156eed8355e4a377a55e9da194a657c- Stable URL of this page
https://metraipolis.com/documento/dc_c82e35eb4f5b
How to cite
Multi-Node Transformers for Object Detection and Captioning Across Distributed Edge Networks — arXiv:2611.11291 — arXiv (en), https://arxiv.org/abs/2611.11291 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c82e35eb4f5b (Metraipolis archive dc_c82e35eb4f5b, sha256 83cd0d3c122293a48bed8e71829d041ec156eed8355e4a377a55e9da194a657c)
BibTeX
@misc{dcc82e35eb4f5b,
title = {Multi-Node Transformers for Object Detection and Captioning Across Distributed Edge Networks — arXiv:2611.11291},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.11291},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c82e35eb4f5b; sha256 83cd0d3c122293a48bed8e71829d041ec156eed8355e4a377a55e9da194a657c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.11291. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This paper presents a unified transformer-based framework for object detection and dense region captioning across distributed edge networks. The architecture uses a shared visual encoder followed by detection, region extraction, and autoregressive language-decoding stages, allowing localization and region description to reuse the same image features. This design removes the second image-encoding path required by decoupled detection and captioning pipelines. To support execution on resource-limited devices, a workload-allocation formulation assigns model stages and input streams across connected edge nodes while accounting for execution time, memory capacity, processor utilization, power limits, and intermediate tensor transfer cost. The framework is evaluated on a six-device edge testbed comprising four NVIDIA Jetson Orin Nano and Orin NX inference nodes and two Raspberry Pi 5 auxiliary CPU nodes, with TensorRT FP16 and INT8 execution on the NVIDIA devices. On a Jetson Orin Nano, the unified INT8 model achieves 38.1 FPS with 3.5 GB peak memory use and 11.8 W measured power. Under four concurrent streams, the proposed allocation achieves 35.2 FPS and 28.4 ms mean end-to-end latency with an internode transfer rate of 6.8 MB/s. Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.DC, nuovi lavori del giorno). Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.11291 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-10T18:38:07.441Z dalla pagina https://arxiv.org/list/cs.DC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).