# MCUBench: A Benchmark of Tiny Object Detectors on MCUs

Source: [MCUBench: A Benchmark of Tiny Object Detectors on MCUs](<https://www.sota2.com/research/paper/68fa74f61e209131cea64da7>)

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

Data updated: 2025-10-26T03:22:19.696Z

Authors: Sudhakar Sah, Darshan C. Ganji, Matteo Grimaldi, Ravish Kumar, Alexander Hoffman, Honnesh Rohmetra, Ehsan Saboori

Published: 2024-09-27T16:02:56.000Z

## Abstract

We introduce MCUBench, a benchmark featuring over 100 YOLO-based object detection models evaluated on the VOC dataset across seven different MCUs. This benchmark provides detailed data on average precision, latency, RAM, and Flash usage for various input resolutions and YOLO-based one-stage detectors. By conducting a controlled comparison with a fixed training pipeline, we collect comprehensive performance metrics. Our Pareto-optimal analysis shows that integrating modern detection heads and training techniques allows various YOLO architectures, including legacy models like YOLOv3, to achieve a highly efficient tradeoff between mean Average Precision (mAP) and latency. MCUBench serves as a valuable tool for benchmarking the MCU performance of contemporary object detectors and aids in model selection based on specific constraints.

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2409.18866>)

[PDF](<https://arxiv.org/pdf/2409.18866.pdf>)
