---
title: "Do sEMG Foundation Models Improve Cross-Subject Generalisation?"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.08199v1"
permalink: "https://feed.astralor.com/items/itm_8e3ff23c509f9f93ec2825cb"
published: "2026-11-05T15:53:37.000Z"
score: 56
channel: "ai"
tags: ["Foundation Models Improve","Cross-Subject Generalisation","Foundation Models","However"]
---

# Do sEMG Foundation Models Improve Cross-Subject Generalisation?

## 速览

sEMG Foundation Models aim to learn general purpose representations over diverse subjects and recording conditions that boost performance on a variety of downstream tasks. However, existing evaluations make it difficult…

## 关键点

- sEMG Foundation Models aim to learn general purpose representations over diverse subjects and recording conditions that boost performance on a variety of downstream tasks.
- However, existing evaluations make it difficult to discern whether pretraining alone is sufficient to combat the cross-subject overfitting which makes machine learning on sEMG so challenging.
- We conduct a systematic evaluation of three sEMG foundation models across three gesture classification datasets under both intra-session and inter-subject splits, using three fine-tuning strategies designed to isolate t…

## 全文

sEMG Foundation Models aim to learn general purpose representations over diverse subjects and recording conditions that boost performance on a variety of downstream tasks. However, existing evaluations make it difficult to discern whether pretraining alone is sufficient to combat the cross-subject overfitting which makes machine learning on sEMG so challenging. We conduct a systematic evaluation of three sEMG foundation models across three gesture classification datasets under both intra-session and inter-subject splits, using three fine-tuning strategies designed to isolate the contribution of pretraining. We find that pretraining boosts performance when train and test samples are drawn from the same recording session, but this benefit largely disappears under inter-subject evaluation. In low subject count datasets, pretraining provides little to no benefit and classical ML baselines match or exceed foundation model performance.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_8e3ff23c509f9f93ec2825cb