mlsanityData to 14 Oct 2026

Online Adaptation via Dual-Stage Alignment and Self-Supervision for Fast-Calibration Brain-Computer Interfaces

arXiv 2509.19403 ↗First posted 23 Sep 2025eess.SP cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Individual differences in brain activity hinder the online application of electroencephalogram (EEG)-based brain computer interface (BCI) systems. To overcome this limitation, this study proposes an online adaptation algorithm for unseen subjects via dual-stage alignment and self-supervision. The alignment process begins by applying Euclidean alignment in the EEG data space and then updates batch normalization statistics in the representation space. Moreover, a self-supervised loss is designed to update the decoder. The loss is computed by soft pseudo-labels derived from the decoder as a proxy for the unknown ground truth, and is calibrated by Shannon entropy to facilitate self-supervised training. Experiments across five public datasets and seven decoders show the proposed algorithm can be integrated seamlessly regardless of BCI paradigm and decoder architecture. In each iteration, the decoder is updated with a single online trial, which yields average accuracy gains of 4.9% on steady-state visual evoked potentials (SSVEP) and 3.6% on motor imagery. These results support fast-calibration operation and show that the proposed algorithm has great potential for BCI applications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 65 references that are in the map. First posted on arXiv 23 Sep 2025.

Builds on

22 of 65 references.

References · 22

  1. 2017On Calibration of Modern Neural Networkscited by 4,960
  2. 2017Neural Discrete Representation Learningcited by 4,712
  3. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  4. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  5. 2016EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfacescited by 628
  6. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 612
  7. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 510
  8. 2015Return of Frustratingly Easy Domain Adaptationcited by 391
  9. 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 288
  10. 2022Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistencycited by 250
  11. 2022Test-Time Training with Masked Autoencoderscited by 212
  12. 2020Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfercited by 173
10 more
  1. 2017Online Adaptation of Convolutional Neural Networks for Video Object Segmentationcited by 109
  2. 2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98
  3. 2022Source-Free Unsupervised Domain Adaptation: A Surveycited by 80
  4. 2018Transfer Learning for Brain-Computer Interfaces: A Euclidean Space Data Alignment Approachcited by 76
  5. 2020Domain Adaptation with Auxiliary Target Domain-Oriented Classifiercited by 76
  6. 2023DELTA: degradation-free fully test-time adaptationcited by 72
  7. 2024T-TIME: Test-Time Information Maximization Ensemble for Plug-and-Play BCIscited by 15
  8. 2024A Systematic Evaluation of Euclidean Alignment with Deep Learning for EEG Decodingcited by 12
  9. 2025Fine-Tuning Strategies for Continual Online EEG Motor Imagery Decoding: Insights from a Large-Scale Longitudinal Studycited by 4
  10. 2024Inter-individual and inter-site neural code conversion without shared stimulicited by 3

Built on by

Not cited yet.