# Personalising a Cross-User Surface Electromyography Encoder Under a Small Calibration Budget

arXiv: https://arxiv.org/abs/2609.20296 · HTML: https://mlsanity.com/paper/2609.20296/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 31 Jul 2026.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)
- [Deep Learning for Electromyographic Hand Gesture Signal Classification Using Transfer Learning](https://mlsanity.com/paper/1801.07756/) (2018)
- [Domain Adaptation for sEMG-based Gesture Recognition with Recurrent Neural Networks](https://mlsanity.com/paper/1901.06958/) (2019)
- [Interpreting Deep Learning Features for Myoelectric Control: A Comparison with Handcrafted Features](https://mlsanity.com/paper/1912.00283/) (2019)
- [A Montage-Agnostic Encoder for Calibration-Light Cross-User Gesture Recognition from Surface Electromyography](https://mlsanity.com/paper/2607.27565/) (2026)
- [Recognition and Label-Free Adaptation Across Recording Sessions in Surface-EMG Gesture Decoding](https://mlsanity.com/paper/2607.27568/) (2026)

## Abstract (arXiv)

A myoelectric interface needs calibration from the user before it will function. Earlier work has treated calibration as a quantity, but has not asked the question of what a device should do with the calibration repetitions once they have been collected. This paper views personalizing the cross-user encoder as a design decision with a cost. Four alternative approaches to using exactly the same labeled repetitions were tested from a single cross-user encoder per held-out subject. Prototypical adaptation, linear probes, scaled fine-tuning and full fine-tuning were tested at every budget up to the maximum each database allows, five repetitions on DB1 and four on DB2 and DB5. Comparing four ways to spend a small calibration budget across 77 subjects, full fine-tuning is the most accurate at every budget, consistently enough that there is no exception among subsets of subjects. The result which impacts how one might make an engineering decision however is that a gradient free prototypical rule recovers 52 to 78 per cent of its benefit with no optimiser and no per-user copy of the weights, which makes personalisation something a worn device can do at donning time. The widespread intuition that a good representation only needs a fresh classifier is incorrect here. How well each method may perform relative to a per-user classifier that would be fitted by a clinic will depend on the specific database.