Metraipolis › archive › dc_fc30e9458dfc
Adaptive AI: Energy Efficient Multi-exit TinyML on Intelligent Vision Systems at the Edge — arXiv:2609.11939
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.11939
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:08:40.310Z
- SHA-256 of the archived text
2f09533ff70aa35b6748736a52c50a5432c689bec8b6463fb4fbd8d2c4b85e41- Stable URL of this page
https://metraipolis.com/documento/dc_fc30e9458dfc
How to cite
Adaptive AI: Energy Efficient Multi-exit TinyML on Intelligent Vision Systems at the Edge — arXiv:2609.11939 — arXiv (en), https://arxiv.org/abs/2609.11939 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fc30e9458dfc (Metraipolis archive dc_fc30e9458dfc, sha256 2f09533ff70aa35b6748736a52c50a5432c689bec8b6463fb4fbd8d2c4b85e41)
BibTeX
@misc{dcfc30e9458dfc,
title = {Adaptive AI: Energy Efficient Multi-exit TinyML on Intelligent Vision Systems at the Edge — arXiv:2609.11939},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.11939},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fc30e9458dfc; sha256 2f09533ff70aa35b6748736a52c50a5432c689bec8b6463fb4fbd8d2c4b85e41},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11939. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Traditional TinyML systems for edge devices achieve high accuracy by relying on fixed-depth models that require a constant number of multiply-accumulate (MAC) operations regardless of the input complexity. This approach wastes critical resources in battery-powered Internet-of-Things (IoT) devices and limits the real-time performance of edge cyber-physical systems. Multi-exit execution schemes mitigate these issues and are widely used on high-end devices such as GPUs, but are rarely exploited on edge IoT devices because they require substantial rethinking given their strict memory and computational constraints. We address these aspects by designing and deploying, on an ultra-low-power GWT GAP9 System-on-Chip (SoC), a novel multi-exit computational scheme, demonstrating it on a MobileNetV2 convolutional neural network (CNN) for the ImageNet-100 classification task. Our approach introduces multiple exits at different CNN depths, each with a confidence-based gating mechanism that dynamically and autonomously decides whether to continue or stop inference. Comparing our multi-exit strategy to the standard MobileNetV2 on a GAP9 SoC, we show a 41% reduction in the average computational cost (from 313 MMAC to 185 MMAC), a 29% lower inference time (from 49 to 35 ms), and an energy saving of 24% (from 2.1 to 1.6 mJ per frame). All these improvements come with a ~1% loss in accuracy compared to the full-depth MobileNetV2, which achieves 80.5%. Finally, comparing our adaptable multi-exit scheme with a third-party state-of-the-art adaptive CNN, also deployed on the GAP9, we achieve more than 2x its computational efficiency, increasing it from 8.1 to 17.2 MAC/cycle. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-14 in cs.DC). Categorie arXiv: Hardware Architecture (cs.AR) ; Computer Vision and Pattern Recognition (cs.CV); Distributed, Parallel, and Cluster Computing (cs.DC). Pagina del lavoro: https://arxiv.org/abs/2609.11939 — 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 2026-10-16T03:03:05.099Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).