# YOLOBench: Benchmarking Efficient Object Detectors on Embedded Systems

arXiv: https://arxiv.org/abs/2307.13901 · HTML: https://mlsanity.com/paper/2307.13901/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 40 references that are in the map.
- First posted on arXiv 26 Jul 2023.

## Builds on (most cited first, 23 of 23)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [RepVGG: Making VGG-style ConvNets Great Again](https://mlsanity.com/paper/2101.03697/) (2021)
- [Pruning neural networks without any data by iteratively conserving synaptic flow](https://mlsanity.com/paper/2006.05467/) (2020)
- [Picking Winning Tickets Before Training by Preserving Gradient Flow](https://mlsanity.com/paper/2002.07376/) (2020)
- [Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection](https://mlsanity.com/paper/2006.04388/) (2020)
- [WIDER FACE: A Face Detection Benchmark](https://mlsanity.com/paper/1511.06523/) (2015)
- [Neural Architecture Search without Training](https://mlsanity.com/paper/2006.04647/) (2020)
- [Zero-Cost Proxies for Lightweight NAS](https://mlsanity.com/paper/2101.08134/) (2021)
- [RTMDet: An Empirical Study of Designing Real-Time Object Detectors](https://mlsanity.com/paper/2212.07784/) (2022)
- [A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS](https://mlsanity.com/paper/2304.00501/) (2023)
- [PP-YOLOE: An evolved version of YOLO](https://mlsanity.com/paper/2203.16250/) (2022)
- [Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition](https://mlsanity.com/paper/2102.01063/) (2021)
- [Precise Detection in Densely Packed Scenes](https://mlsanity.com/paper/1904.00853/) (2019)
- [YOLOv6 v3.0: A Full-Scale Reloading](https://mlsanity.com/paper/2301.05586/) (2023)
- [ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradients](https://mlsanity.com/paper/2301.11300/) (2023)
- [Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets](https://mlsanity.com/paper/2010.14819/) (2020)
- [DAMO-YOLO : A Report on Real-Time Object Detection Design](https://mlsanity.com/paper/2211.15444/) (2022)

## Built on by (most cited first, 5 of 5)

- [Small Object Detection for Indoor Assistance to the Blind using YOLO NAS Small and Super Gradients](https://mlsanity.com/paper/2409.07469/) (2024)
- [ActNAS : Generating Efficient YOLO Models using Activation NAS](https://mlsanity.com/paper/2410.10887/) (2024)
- [Efficient Vision-based Vehicle Speed Estimation](https://mlsanity.com/paper/2505.01203/) (2025)
- [YOLO-NAS-Bench: A Surrogate Benchmark with Self-Evolving Predictors for YOLO Architecture Search](https://mlsanity.com/paper/2603.09405/) (2026)
- [Input Resolution Matters: Real-Time Object Detection Latency](https://mlsanity.com/paper/2609.12920/) (2026)

## Abstract (arXiv)

We present YOLOBench, a benchmark comprised of 550+ YOLO-based object detection models on 4 different datasets and 4 different embedded hardware platforms (x86 CPU, ARM CPU, Nvidia GPU, NPU). We collect accuracy and latency numbers for a variety of YOLO-based one-stage detectors at different model scales by performing a fair, controlled comparison of these detectors with a fixed training environment (code and training hyperparameters). Pareto-optimality analysis of the collected data reveals that, if modern detection heads and training techniques are incorporated into the learning process, multiple architectures of the YOLO series achieve a good accuracy-latency trade-off, including older models like YOLOv3 and YOLOv4. We also evaluate training-free accuracy estimators used in neural architecture search on YOLOBench and demonstrate that, while most state-of-the-art zero-cost accuracy estimators are outperformed by a simple baseline like MAC count, some of them can be effectively used to predict Pareto-optimal detection models. We showcase that by using a zero-cost proxy to identify a YOLO architecture competitive against a state-of-the-art YOLOv8 model on a Raspberry Pi 4 CPU. The code and data are available at https://github.com/Deeplite/deeplite-torch-zoo