ODEI: Object Detector Efficiency Index

Abstract

Object detectors often rely on multiple metrics to reflect their accuracy and speed performances independently. This article introduces object detector efficiency index (ODEI), a hardware-agnostic metric designed to assess object detector efficiency based on speed-normalized accuracy, utilizing established concepts including mean average precision (mAP) and floating-point operations (FLOPs). By defining seven mandatory parameters that must be specified when ODEI is invoked, the article aims to clarify long-standing confusions within literature regarding evaluation metrics and promote fair and transparent benchmarking research in the object detection space. Usage demonstration of ODEI using state-of-the-art (SOTA) YOLOv12 and RT-DETRv3 studies is also included.