mlsanityData to 14 Oct 2026

Flexible and Fully Quantized Ultra-Lightweight TinyissimoYOLO for Ultra-Low-Power Edge Systems

arXiv 2307.05999 ↗First posted 12 Jul 2023cs.CV eess.IVcited by 11

Not on the map. Why?

Abstract (arXiv)

This paper deploys and explores variants of TinyissimoYOLO, a highly flexible and fully quantized ultra-lightweight object detection network designed for edge systems with a power envelope of a few milliwatts. With experimental measurements, we present a comprehensive characterization of the network's detection performance, exploring the impact of various parameters, including input resolution, number of object classes, and hidden layer adjustments. We deploy variants of TinyissimoYOLO on state-of-the-art ultra-low-power extreme edge platforms, presenting an in-depth a comparison on latency, energy efficiency, and their ability to efficiently parallelize the workload. In particular, the paper presents a comparison between a novel parallel RISC-V processor (GAP9 from Greenwaves) with and without use of its on-chip hardware accelerator, an ARM Cortex-M7 core (STM32H7 from ST Microelectronics), two ARM Cortex-M4 cores (STM32L4 from STM and Apollo4b from Ambiq), and a multi-core platform with a CNN hardware accelerator (Analog Devices MAX78000). Experimental results show that the GAP9's hardware accelerator achieves the lowest inference latency and energy at 2.12ms and 150uJ respectively, which is around 2x faster and 20% more efficient than the next best platform, the MAX78000. The hardware accelerator of GAP9 can even run an increased resolution version of TinyissimoYOLO with 112x112 pixels and 10 detection classes within 3.2ms, consuming 245uJ. To showcase the competitiveness of a versatile general-purpose system we also deployed and profiled a multi-core implementation on GAP9 at different operating points, achieving 11.3ms with the lowest-latency and 490uJ with the most energy-efficient configuration. With this paper, we demonstrate the suitability and flexibility of TinyissimoYOLO on state-of-the-art detection datasets for real-time ultra-low-power edge inference.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 37 of its 68 references that are in the map. First posted on arXiv 12 Jul 2023.

Builds on

37 of 68 references.

References · 37

  1. 2020End-to-End Object Detection with Transformerscited by 7,414
  2. 2017Mask R-CNNcited by 7,277
  3. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  5. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  6. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  7. 2018YOLOv3: An Incremental Improvementcited by 2,659
  8. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  9. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
  10. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  11. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 982
  12. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 482
25 more
  1. 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 275
  2. 2020MCUNet: Tiny Deep Learning on IoT Devicescited by 273
  3. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 263
  4. 2019Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mappingcited by 184
  5. 2020TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systemscited by 165
  6. 2018CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUscited by 121
  7. 2019A Survey of Deep Learning-based Object Detectioncited by 106
  8. 2018Fusion++: Volumetric Object-Level SLAMcited by 98
  9. 2019Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networkscited by 90
  10. 2021MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learningcited by 89
  11. 2020Efficient RGB-D Semantic Segmentation for Indoor Scene Analysiscited by 84
  12. 2020HAWQV3: Dyadic Neural Network Quantizationcited by 60
  13. 2020DORY: Automatic End-to-End Deployment of Real-World DNNs on Low-Cost IoT MCUscited by 58
  14. 2020μNAS: Constrained Neural Architecture Search for Microcontrollerscited by 55
  15. 2019SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollerscited by 52
  16. 2019Memory-Driven Mixed Low Precision Quantization For Enabling Deep Network Inference On Microcontrollerscited by 33
  17. 2022Machine Learning for Microcontroller-Class Hardware: A Reviewcited by 28
  18. 2021Fully Onboard AI-powered Human-Drone Pose Estimation on Ultra-low Power Autonomous Flying Nano-UAVscited by 24
  19. 2021Vega: A 10-Core SoC for IoT End-Nodes with DNN Acceleration and Cognitive Wake-Up From MRAM-Based State-Retentive Sleep Modecited by 18
  20. 2023TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Object Detection Network for Low Power Microcontrollerscited by 18
  21. 2023Lightweight Neural Architecture Search for Temporal Convolutional Networks at the Edgecited by 15
  22. 2022Long-Term Localization using Semantic Cues in Floor Plan Mapscited by 12
  23. 2023Marsellus: A Heterogeneous RISC-V AI-IoT End-Node SoC with 2-to-8b DNN Acceleration and 30%-Boost Adaptive Body Biasingcited by 8
  24. 2021CPPE-5: Medical Personal Protective Equipment Datasetcited by 5
  25. 2023Free Bits: Latency Optimization of Mixed-Precision Quantized Neural Networks on the Edgecited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 5; 2026: 3.

11 papers.

  1. 2023Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLOcited by 15
  2. 2025Benchmarking Ultra-Low-Power μNPUscited by 6
  3. 2024DSORT-MCU: Detecting Small Objects in Real-Time on Microcontroller Unitscited by 4
  4. 2025ELASTIC: Efficient Once For All Iterative Search for Object Detection on Microcontrollerscited by 3
  5. 2024Embedded Machine Learning for Solar PV Power Regulation in a Remote Microgridcited by 2
  6. 2025On-Device Training of PV Power Forecasting Models in a Smart Meter for Grid Edge Intelligencecited by 1
  7. 2025Designing Object Detection Models for TinyML: Foundations, Comparative Analysis, Challenges, and Emerging Solutionscited by 1
  8. 2025TinyEcoWeedNet: Edge Efficient Real-Time Aerial Agricultural Weed Detectioncited by 0
  9. 2026On-Meter Graph Machine Learning: A Case Study of PV Power Forecasting for Grid Edge Intelligencecited by 0
  10. 2026MR2-ByteTrack: CNN and Transformer-based Video Object Detection for AI-augmented Embedded Vision Sensor Nodescited by 0
  11. 2026Energy Constrained Hierarchical Underwater Monitoring via Local Multi-Agent RAGcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023ULEEN: A Novel Architecture for Ultra Low-Energy Edge Neural Networks
  2. 2022BED: A Real-Time Object Detection System for Edge Devices
  3. 2025Efficient Edge Deployment of Quantized YOLOv4-Tiny for Aerial Emergency Object Detection on Raspberry Pi 5
  4. 2025Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications
  5. 2026Achieving Near-Zero-Overhead Multi-Model Hierarchical Classification in Real-Time Detection Pipelines
  6. 2023OISA: Architecting an Optical In-Sensor Accelerator for Efficient Visual Computing
  7. 2022LPYOLO: Low Precision YOLO for Face Detection on FPGA
  8. 2026Zeros can be Informative: Masked Binary U-Net for Image Segmentation on Tensor Cores