msf-CNN: Patch-based Multi-Stage Fusion with Convolutional Neural Networks for TinyML

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Huang, Zhaolan, Baccelli, Emmanuel
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915559040352256
author Huang, Zhaolan
Baccelli, Emmanuel
author_facet Huang, Zhaolan
Baccelli, Emmanuel
contents AI spans from large language models to tiny models running on microcontrollers (MCUs). Extremely memory-efficient model architectures are decisive to fit within an MCU's tiny memory budget e.g., 128kB of RAM. However, inference latency must remain small to fit real-time constraints. An approach to tackle this is patch-based fusion, which aims to optimize data flows across neural network layers. In this paper, we introduce msf-CNN, a novel technique that efficiently finds optimal fusion settings for convolutional neural networks (CNNs) by walking through the fusion solution space represented as a directed acyclic graph. Compared to previous work on CNN fusion for MCUs, msf-CNN identifies a wider set of solutions. We published an implementation of msf-CNN running on various microcontrollers (ARM Cortex-M, RISC-V, ESP32). We show that msf-CNN can achieve inference using 50% less RAM compared to the prior art (MCUNetV2 and StreamNet). We thus demonstrate how msf-CNN offers additional flexibility for system designers.
format Preprint
id arxiv_https___arxiv_org_abs_2505_11483
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle msf-CNN: Patch-based Multi-Stage Fusion with Convolutional Neural Networks for TinyML
Huang, Zhaolan
Baccelli, Emmanuel
Machine Learning
Performance
AI spans from large language models to tiny models running on microcontrollers (MCUs). Extremely memory-efficient model architectures are decisive to fit within an MCU's tiny memory budget e.g., 128kB of RAM. However, inference latency must remain small to fit real-time constraints. An approach to tackle this is patch-based fusion, which aims to optimize data flows across neural network layers. In this paper, we introduce msf-CNN, a novel technique that efficiently finds optimal fusion settings for convolutional neural networks (CNNs) by walking through the fusion solution space represented as a directed acyclic graph. Compared to previous work on CNN fusion for MCUs, msf-CNN identifies a wider set of solutions. We published an implementation of msf-CNN running on various microcontrollers (ARM Cortex-M, RISC-V, ESP32). We show that msf-CNN can achieve inference using 50% less RAM compared to the prior art (MCUNetV2 and StreamNet). We thus demonstrate how msf-CNN offers additional flexibility for system designers.
title msf-CNN: Patch-based Multi-Stage Fusion with Convolutional Neural Networks for TinyML
topic Machine Learning
Performance
url https://arxiv.org/abs/2505.11483