Cross-Subject Generalization

Follow this topic Ask about this topic

Latest papers

9 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Do sEMG Foundation Models Improve Cross-Subject Generalisation?
Nov 5, 2026William Raftery, Dario FarinaCross-Subject Generalization Surface Electromyography
Imperial College London
MultiMental-IAS: A Multimodal Driver Mental State Analysis Dataset for Context-Aware Non-IID Evaluation
Nov 2, 2026Baran Can Gül, Nagendra Pal Singh, Anjana Arvind NaikCross-Subject Generalization Multimodal Dataset
Institute of Industrial Automation and Software Engineering (IAS), University of Stuttgart, Stuttgart, Germany
Ampe-DB: A Dataset for Human Activity and Interaction Analysis Using the Ghanaian Game Ampe
Oct 23, 2026Ruth Senior Biney, Isaac Kojo Yedonu AboahCross-Subject Generalization Human Activity Recognition
Orthogonal Ensembles and Tested Explanations for Performer-Independent Body-Motion Emotion Recognition
Sep 2, 2026Naoto Nishida, Yoshio IshiguroCross-Subject Generalization Emotion Recognition
The University of Tokyo Tokyo, Japan
A comparative and critical study of EEGNet for fNIRS-driven cognitive load classification
Jun 15, 2026Mehshan Ahmed Khan, Houshyar Asadi, Li Zhang +8Cross-Subject Generalization
Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Geelong Warun Ponds Campus, Victoria 3216, Australia · Department of Computer Science, Royal Holloway, University of London, Surrey TW20 0EX, United Kingdom · College of Science and Engineering, James Cook University, Townsville, QLD 4814, Australia +4
Resource-Constrained Affect Modelling via Variance Regularisation Pruning
May 26, 2026Kosmas Pinitas, Konstantinos KatsifisCross-Subject Generalization Cost-Aware Inference
Mediterranean College, Athens, Greece · University of Derby, Derby, UK
BioFormer: Rethinking Cross-Subject Generalization via Spectral Structural Alignment in Biomedical Time-Series
May 21, 2026Guikang Du, Haoran Li, Xinyu Liu +3Cross-Subject Generalization Frequency-Domain Feature Learning
College of Computer Science, Nankai University, Tianjin, China · College of Cyber Science, Tianjin Key Laboratory of Interventional Brain-Computer Interface and Intelligent Rehabilitation, Key Lab of Data and Intelligent System Security, Frontiers Science Center for New Organic Matter, Nankai University, Tianjin, China
From Muscle Bursts to Motor Intent: Self-Supervised Token Modeling for Heterogeneous EMG
May 5, 2026Zhenghao Huang, Huilin Yao, Kaikai WangEMG-Based Gesture Recognition Cross-Subject Generalization
South China University of Technology
Cross-Subject Generalization for EEG Decoding: A Survey of Deep Learning Methods
Apr 29, 2026Taida Li, Yujun Yan, Fei Dou +2Cross-Subject EEG Decoding Cross-Subject Generalization
Department of Computer Science, University of North Carolina at Charlotte, Charlotte, United States · Department of Computer Science, Dartmouth College, Hanover, United States · School of Computing, University of Georgia, Athens, United States +1

Nov 5, 2026J/K move · Enter open · S save

Do sEMG Foundation Models Improve Cross-Subject Generalisation?

William Raftery, Dario Farina

Imperial College London

Cross-Subject Generalization Surface Electromyography EMG-Based Gesture Recognition

Open paper AskPDF arXiv

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.