# On-Device Vision Training, Deployment, and Inference on a Thumb-Sized Microcontroller

arXiv: https://arxiv.org/abs/2604.23012 · HTML: https://mlsanity.com/paper/2604.23012/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 19 references that are in the map.
- First posted on arXiv 24 Apr 2026.

## Builds on (most cited first, 7 of 7)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [On-Device Training Under 256KB Memory](https://mlsanity.com/paper/2206.15472/) (2022)
- [TinyOL: TinyML with Online-Learning on Microcontrollers](https://mlsanity.com/paper/2103.08295/) (2021)
- [Tiny Machine Learning: Progress and Futures](https://mlsanity.com/paper/2403.19076/) (2024)
- [On-device Online Learning and Semantic Management of TinyML Systems](https://mlsanity.com/paper/2405.07601/) (2024)
- [Send Less, Save More: Energy-Efficiency Benchmark of Embedded CNN Inference vs. Data Transmission in IoT](https://mlsanity.com/paper/2510.24829/) (2025)
- [TinyTorch: Building Machine Learning Systems from First Principles](https://mlsanity.com/paper/2601.19107/) (2026)

## Abstract (arXiv)

This paper presents a complete, end-to-end on-device vision machine learning pipeline, comprising data acquisition, two-layer CNN training with Adam optimization, and real-time inference, executing entirely on a microcontroller-class device costing 15-40 USD. Unlike cloud-based workflows that require external infrastructure and conceal the computational pipeline from the practitioner, this system implements every step of the core ML lifecycle in approximately 1,750 lines of readable C++ that compiles in under one minute using the Arduino IDE, with no external ML dependencies. Running on the Seeed Studio ESP32-S3 XIAO ML Kit (8 MB PSRAM), the firmware achieves three-class 64x64 image classification in approximately 9 minutes per training run, with real-time inference at 6.3 FPS. Key contributions include: correct batch-level gradient accumulation; pre-computed resize lookup tables for inference; dual-format weight export for SD-free baked-in deployment; a three-tier weight priority system (SD binary > baked-in header > He-initialization) resolved automatically at boot; a single-constant network reconfiguration interface; and PSRAM-aware memory management suited to microcontroller constraints. All source code and reference datasets are released under the MIT License at https://github.com/webmcu-ai/on-device-vision-ai