# XiYOLO: Energy-Aware Object Detection via Iterative Architecture Search and Scaling

Source: [XiYOLO: Energy-Aware Object Detection via Iterative Architecture Search and Scaling](<https://www.sota2.com/research/paper/6a01628fdbc836b87d8230d0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-12T05:00:04.827Z

Authors: Tony Tran, Richie R. Suganda, Bin Hu

Published: 2026-05-07T20:38:06.000Z

## Abstract

Object detection on heterogeneous edge devices must satisfy strict energy, latency, and memory constraints while still providing reliable perception for downstream autonomy. Existing energy-aware NAS methods often target limited deployment settings, while real energy remains difficult to optimize because it is highly device-dependent and costly to measure. We address these challenges with an energy-adaptive framework that combines an energy-aware XiResOFA search space, a two-stage energy estimator, and iterative search to identify a single energy-efficient base architecture. We then apply compound scaling to transform this base design into the XiYOLO family across deployment budgets, enabling interpretable accuracy-energy tradeoffs under sparse hardware measurements. Experiments on PascalVOC, COCO, and real-device deployment show that XiYOLO achieves a stronger energy-accuracy tradeoff than YOLO baselines. On PascalVOC, the medium XiYOLO model reaches 86.15 mAP50 while reducing energy relative to YOLOv12m by 20.6% on GPU and 35.9% on NPU. On COCO, XiYOLO reduces energy relative to YOLOv12 by up to 53.7% on GPU and 51.6% on NPU at the small scale. The proposed two-stage estimator also improves sample efficiency over a joint predictor under few-shot adaptation with only 2-20 target-device samples.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Object Detection on COCO (val) (Hardware Power Efficiency)](<https://www.sota2.com/research/sota/object-detection-on-coco-val-hardware-power-efficiency.md>): Object Detection; COCO (val); mAP50-95: 50.7.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.06927>)

[PDF](<https://arxiv.org/pdf/2605.06927.pdf>)