mlsanityData to 7 Oct 2026

MinUn: Accurate ML Inference on Microcontrollers

arXiv 2210.16556 ↗First posted 29 Oct 2022cs.LG cs.PLcited by 3

Not on the map. Why?

Abstract (arXiv)

Running machine learning inference on tiny devices, known as TinyML, is an emerging research area. This task requires generating inference code that uses memory frugally, a task that standard ML frameworks are ill-suited for. A deployment framework for TinyML must be a) parametric in the number representation to take advantage of the emerging representations like posits, b) carefully assign high-precision to a few tensors so that most tensors can be kept in low-precision while still maintaining model accuracy, and c) avoid memory fragmentation. We describe MinUn, the first TinyML framework that holistically addresses these issues to generate efficient code for ARM microcontrollers (e.g., Arduino Uno, Due and STM32H747) that outperforms the prior TinyML frameworks.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 37 of its 101 references that are in the map. First posted on arXiv 29 Oct 2022.

Builds on

37 of 101 references.

References · 37

  1. 2016Densely Connected Convolutional Networkscited by 6,691
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  4. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  5. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  6. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  7. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 741
  8. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 697
  9. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 666
  10. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 507
  11. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 426
  12. 2019Data-Free Quantization Through Weight Equalization and Bias Correctioncited by 328
25 more
  1. 2015WIDER FACE: A Face Detection Benchmarkcited by 297
  2. 2020MCUNet: Tiny Deep Learning on IoT Devicescited by 269
  3. 2019Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networkscited by 234
  4. 2017Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weightscited by 211
  5. 2016Convolutional Neural Networks using Logarithmic Data Representationcited by 97
  6. 2021MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learningcited by 87
  7. 2017Training Quantized Nets: A Deeper Understandingcited by 74
  8. 2015Neural Networks with Few Multiplicationscited by 46
  9. 2019Same, Same But Different - Recovering Neural Network Quantization Error Through Weight Factorizationcited by 45
  10. 2017FaceBoxes: A CPU Real-time Face Detector with High Accuracycited by 44
  11. 2017Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networkscited by 43
  12. 2019FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Networkcited by 38
  13. 2019SqueezeNAS: Fast neural architecture search for faster semantic segmentationcited by 31
  14. 2018Rethinking floating point for deep learningcited by 22
  15. 2019LFFD: A Light and Fast Face Detector for Edge Devicescited by 21
  16. 2020RNNPool: Efficient Non-linear Pooling for RAM Constrained Inferencecited by 21
  17. 2018Simultaneously Optimizing Weight and Quantizer of Ternary Neural Network using Truncated Gaussian Approximationcited by 20
  18. 2018Detecting Heads using Feature Refine Net and Cascaded Multi-Scale Architecturecited by 18
  19. 2019EXTD: Extremely Tiny Face Detector via Iterative Filter Reusecited by 18
  20. 2018Per-Tensor Fixed-Point Quantization of the Back-Propagation Algorithmcited by 15
  21. 2017ShiftCNN: Generalized Low-Precision Architecture for Inference of Convolutional Neural Networkscited by 13
  22. 2019Focused Quantization for Sparse CNNscited by 5
  23. 2013On Sound Compilation of Realscited by 4
  24. 2018Heterogeneous Bitwidth Binarization in Convolutional Neural Networkscited by 3
  25. 2021MAFIA: Machine Learning Acceleration on FPGAs for IoT Applicationscited by 2

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 0; 2025: 2.

3 papers.

  1. 2023A Machine Learning-oriented Survey on Tiny Machine Learningcited by 26
  2. 2025Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applicationscited by 6
  3. 2025EdgeMark: An Automation and Benchmarking System for Embedded Artificial Intelligence Toolscited by 2