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

TL;DR

XiYOLO introduces an energy-aware neural architecture search framework that optimizes object detection models for edge devices by balancing accuracy and energy consumption, with strong results on standard datasets.

Contribution

The paper proposes a novel energy-adaptive search framework combining a new search space, a two-stage energy estimator, and iterative search for efficient architecture design.

Findings

XiYOLO achieves 20-54% energy reduction over YOLO baselines.

The medium XiYOLO model reaches 86.15 mAP50 on PascalVOC.

The two-stage estimator improves sample efficiency in device-specific adaptation.

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.