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

arXiv: https://arxiv.org/abs/2509.19403 · HTML: https://mlsanity.com/paper/2509.19403/

## 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 (most cited first, 22 of 22)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces](https://mlsanity.com/paper/1611.08024/) (2016)
- [Deep Transfer Learning with Joint Adaptation Networks](https://mlsanity.com/paper/1605.06636/) (2016)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [Return of Frustratingly Easy Domain Adaptation](https://mlsanity.com/paper/1511.05547/) (2015)
- [Revisiting Batch Normalization For Practical Domain Adaptation](https://mlsanity.com/paper/1603.04779/) (2016)
- [Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency](https://mlsanity.com/paper/2206.08496/) (2022)
- [Test-Time Training with Masked Autoencoders](https://mlsanity.com/paper/2209.07522/) (2022)
- [Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer](https://mlsanity.com/paper/2012.07297/) (2020)
- [Online Adaptation of Convolutional Neural Networks for Video Object Segmentation](https://mlsanity.com/paper/1706.09364/) (2017)
- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [Transfer Learning for Brain-Computer Interfaces: A Euclidean Space Data Alignment Approach](https://mlsanity.com/paper/1808.05464/) (2018)
- [Domain Adaptation with Auxiliary Target Domain-Oriented Classifier](https://mlsanity.com/paper/2007.04171/) (2020)
- [DELTA: degradation-free fully test-time adaptation](https://mlsanity.com/paper/2301.13018/) (2023)
- [T-TIME: Test-Time Information Maximization Ensemble for Plug-and-Play BCIs](https://mlsanity.com/paper/2412.07228/) (2024)
- [A Systematic Evaluation of Euclidean Alignment with Deep Learning for EEG Decoding](https://mlsanity.com/paper/2401.10746/) (2024)
- [Fine-Tuning Strategies for Continual Online EEG Motor Imagery Decoding: Insights from a Large-Scale Longitudinal Study](https://mlsanity.com/paper/2502.06828/) (2025)
- [Inter-individual and inter-site neural code conversion without shared stimuli](https://mlsanity.com/paper/2403.11517/) (2024)

## 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.