# YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design

arXiv: https://arxiv.org/abs/2009.05697 · HTML: https://mlsanity.com/paper/2009.05697/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Sep 2020.

## Built on by (most cited first, 24 of 24)

- [PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices](https://mlsanity.com/paper/2111.00902/) (2021)
- [Binary Complex Neural Network Acceleration on FPGA](https://mlsanity.com/paper/2108.04811/) (2021)
- [Towards Artificial General Intelligence (AGI) in the Internet of Things (IoT): Opportunities and Challenges](https://mlsanity.com/paper/2309.07438/) (2023)
- [FORMS: Fine-grained Polarized ReRAM-based In-situ Computation for Mixed-signal DNN Accelerator](https://mlsanity.com/paper/2106.09144/) (2021)
- [Towards More Efficient EfficientDets and Low-Light Real-Time Marine Debris Detection](https://mlsanity.com/paper/2203.07155/) (2022)
- [Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Acceleration](https://mlsanity.com/paper/2111.11581/) (2021)
- [Towards Fast and Accurate Multi-Person Pose Estimation on Mobile Devices](https://mlsanity.com/paper/2106.15304/) (2021)
- [An Empirical Study of Adder Neural Networks for Object Detection](https://mlsanity.com/paper/2112.13608/) (2021)
- [FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffs](https://mlsanity.com/paper/2301.06719/) (2023)
- [Plug-and-Play Versatile Compressed Video Enhancement](https://mlsanity.com/paper/2504.15380/) (2025)
- [R-TOSS: A Framework for Real-Time Object Detection using Semi-Structured Pruning](https://mlsanity.com/paper/2303.02191/) (2023)
- [DIR-BHRNet: A Lightweight Network for Real-time Vision-based Multi-person Pose Estimation on Smartphones](https://mlsanity.com/paper/2407.13777/) (2024)
- [Mobile Augmented Reality with Federated Learning in the Metaverse](https://mlsanity.com/paper/2212.08324/) (2022)
- [All-in-One Image Compression and Restoration](https://mlsanity.com/paper/2502.03649/) (2025)
- [Edge-InversionNet: Enabling Efficient Inference of InversionNet on Edge Devices](https://mlsanity.com/paper/2310.09667/) (2023)
- [Hermes: Memory-Efficient Pipeline Inference for Large Models on Edge Devices](https://mlsanity.com/paper/2409.04249/) (2024)
- [PointSplit: Towards On-device 3D Object Detection with Heterogeneous Low-power Accelerators](https://mlsanity.com/paper/2504.03654/) (2025)
- [AyE-Edge: Automated Deployment Space Search Empowering Accuracy yet Efficient Real-Time Object Detection on the Edge](https://mlsanity.com/paper/2408.05363/) (2024)
- [Designing Object Detection Models for TinyML: Foundations, Comparative Analysis, Challenges, and Emerging Solutions](https://mlsanity.com/paper/2508.08352/) (2025)
- [CoCoPIE XGen: A Full-Stack AI-Oriented Optimizing Framework](https://mlsanity.com/paper/2206.10620/) (2022)
- [Multi-Objective Evolutionary for Object Detection Mobile Architectures Search](https://mlsanity.com/paper/2211.02791/) (2022)
- [A Novel Compression Framework for YOLOv8: Achieving Real-Time Aerial Object Detection on Edge Devices via Structured Pruning and Channel-Wise Distillation](https://mlsanity.com/paper/2509.12918/) (2025)
- [From Camera-Based Sensing to Reasoning: A Comprehensive Review Toward Proactive Vulnerable Road User Safety](https://mlsanity.com/paper/2510.03314/) (2025)
- [Real-Time Threaded Houbara Detection and Segmentation for Wildlife Conservation using Mobile Platforms](https://mlsanity.com/paper/2510.03501/) (2025)

## Abstract (arXiv)

The rapid development and wide utilization of object detection techniques have aroused attention on both accuracy and speed of object detectors. However, the current state-of-the-art object detection works are either accuracy-oriented using a large model but leading to high latency or speed-oriented using a lightweight model but sacrificing accuracy. In this work, we propose YOLObile framework, a real-time object detection on mobile devices via compression-compilation co-design. A novel block-punched pruning scheme is proposed for any kernel size. To improve computational efficiency on mobile devices, a GPU-CPU collaborative scheme is adopted along with advanced compiler-assisted optimizations. Experimental results indicate that our pruning scheme achieves 14× compression rate of YOLOv4 with 49.0 mAP. Under our YOLObile framework, we achieve 17 FPS inference speed using GPU on Samsung Galaxy S20. By incorporating our proposed GPU-CPU collaborative scheme, the inference speed is increased to 19.1 FPS, and outperforms the original YOLOv4 by 5× speedup. Source code is at: urlhttps://github.com/nightsnack/YOLObile.