Memory-Augmented Online Test-Time Adaptation for EEG Motor Imagery via Perturbation Consistency and Confidence Calibration

Kunkun Zhang; Kehao Wu; Zhitao Chen; Haigen Hu; Qianwei Zhou

cs.LGOct 21, 2026

Memory-Augmented Online Test-Time Adaptation for EEG Motor Imagery via Perturbation Consistency and Confidence Calibration

Authors: Kunkun Zhang, Kehao Wu, Zhitao Chen, Haigen Hu, Qianwei Zhou

Organizations: College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, China · Zhejiang Key Laboratory of Visual Information Intelligent Processing, Hangzhou 310023, China

Abstract

Recently, electroencephalography (EEG)-based brain--computer interfaces (BCIs) have gained traction as portable neural measurement systems. However, the practical deployment of these instruments is often hindered by nonstationarity and cross-subject distribution shifts, which lead to significant intersubject inconsistency. Existing adaptation methods remain impractical for real-time measurement scenarios, as they typically require offline access to source or aggregated target data. To address these challenges, this article proposes memory-augmented online test-time adaptation (OTTA) with perturbation consistency and confidence calibration (MOPC), a source-free framework designed to enhance the reliability of BCI instrumentation. MOPC enables the measurement system to update its decoding parameters on the fly during the inference stage, facilitating single-pass adaptation without accessing sensitive source data. We introduce random-mask perturbations to enforce prediction consistency against inherent EEG signal noise and acquisition artifacts. Furthermore, a confidence-calibrated reweighting loss is designed to integrate feature-space similarity, effectively mitigating unreliable pseudolabels and class imbalance during continuous signal acquisition. To ensure system stability and prevent the catastrophic forgetting of established neural patterns, a lightweight memory module is incorporated to regularize parameter updates within a tight latency budget. Evaluated on the BCI IV IIb and OpenBMI datasets, MOPC achieves state-of-the-art performance, outperforming prior methods by 2.22~% and 3.67~%, respectively, while keeping the per-trial adaptation latency to approximately 40--60 ms. This study provides a robust, recalibration-free solution for real-time EEG decoding, marking a significant advancement in the precision and usability of practical BCI measurement instruments.

Figures & tables

Fig. 1: Conceptual comparison of three domain-adaptation paradigms for cross-subject EEG decoding. (a) UDA. (b) SFUDA. (c) OTTA.

Fig. 2: Overview of MOPC. Top (offline training): EEG data from $K$ source subjects are prealigned and concatenated to train an $N$ -model ensemble via cross-entropy loss $\mathcal{L}_{\mathrm{ce}}$ . Bottom (online testing): For each trial $x_{t}^{m}$ in the real-time measurement stream: 1) inference: the trial is prealigned and evaluated by the ensemble to yield the soft-voted prediction $\hat{y}_{t}^{m}$ , while the aligned data is pushed to the FIFO memory bank; and 2) adaptation: a random-mask view is generated to compute $\mathcal{L}_{\mathrm{pcr}}$ and $\mathcal{L}_{\mathrm{jem}}$ . Simultaneously, a pairwise feature-similarity matrix is constructed from the memory bank to derive the confidence-calibrated loss $\mathcal{L}_{\mathrm{ccr}}$ . The framework minimizes the hybrid loss to update the BN parameters of ensemble members sequentially in a round-robin fashion, ensuring a highly efficient, single-pass adaptation.

Signal acquisition and preprocessing
Parameter	Value	Note
Sampling rate	250 Hz (IIb); 1000 $\rightarrow$ 250 Hz (OpenBMI)	OpenBMI down-sampled for online efficiency
EEG channels $C$	3 (IIb: C3/Cz/C4); 20 (OpenBMI)	OpenBMI uses a 20-channel subset of 62
Trial window	4 s $=1000$ samples ( $T$ )	$0$ – $4$ s after the cue, at 250 Hz
Band-pass filter	4–40 Hz, 5th-order Butterworth (IIb); 8–30 Hz (OpenBMI)
Offline source-model training

TABLE I: Consolidated experimental configuration for reproducibility. All values are those reported in the text; the table gathers them into a single reference

Category	Method	B01	B02	B03	B04	B05	B06	B07	B08	B09	Avg. acc $\pm$ std
DT	EEGNet	73.12	61.79	56.87	88.75	80.94	75.94	76.88	84.38	87.81	76.28 $\pm$ 11.03 **
	ConvNet	63.75	59.29	54.69	93.75	71.25	74.38	74.06	80.63	86.25	73.12 $\pm$ 12.64 **
	LMDANet	72.81	60.00	55.94	90.31	73.12	82.50	76.56	81.87	86.56	75.52 $\pm$ 11.55 **
DA	DANN	73.75	62.50	57.50	89.69	86.25	76.88	76.56	84.06	87.50	77.19 $\pm$ 11.22 **
DA	SHOT	75.31	59.29	57.81	95.94	84.38	74.38	80.94	90.62	86.25	78.32 $\pm$ 13.11 *
TTA	TENT	73.12	57.86	54.69	96.56	83.44	78.75	78.75	89.69	84.38	77.47 $\pm$ 13.80 **

TABLE II: Class-balanced cross-subject classification accuracies on BCI IV IIb (%)

Category	Method	Average	Std	F1	Kappa
DT	EEGNet	73.57 ***	12.66	74.71	47.14
	ConvNet	72.83 ***	12.92	73.85	45.66
	LMDANet	70.17 ***	15.52	68.76	40.33
DA	DANN	73.82 ***	12.71	74.76	47.64
DA	SHOT	74.32 **	12.53	75.14	48.64
TTA	TENT	74.21 ***	12.49	75.31	48.42

TABLE III: Class-balanced cross-subject classification accuracies on OpenBMI (%)

Category	Method	BCI IV IIb	OpenBMI
DT	EEGNet	76.75 $\pm$ 0.76	74.99 $\pm$ 0.43
	ConvNet	74.96 $\pm$ 0.83	73.42 $\pm$ 0.57
	LMDANet	76.31 $\pm$ 0.63	72.67 $\pm$ 0.39
DA	DANN	76.20 $\pm$ 0.72	74.31 $\pm$ 0.53
DA	SHOT	77.21 $\pm$ 0.57	75.21 $\pm$ 0.37
TTA	TENT	76.93 $\pm$ 0.64	75.17 $\pm$ 0.46

TABLE IV: Class-imbalanced cross-subject accuracy (%) on BCI IV IIb and OpenBMI

Dataset	Model	Acc $\pm$ std	Kappa $\pm$ std
BCI IV IIb	baseline	76.28 $\pm$ 0.42	52.55 $\pm$ 0.83
	w/o $\mathcal{L}_{pcr}$	80.32 $\pm$ 0.24	60.64 $\pm$ 0.47
	w/o $\mathcal{L}_{jem}$	79.67 $\pm$ 0.15	59.33 $\pm$ 0.29
	w/o $\mathcal{L}_{ccr}$	79.58 $\pm$ 0.15	59.16 $\pm$ 0.31
	Whole	81.23 $\pm$ 0.11	61.99 $\pm$ 0.23
OpenBMI	baseline	73.57 $\pm$ 0.34	50.07 $\pm$ 0.67

TABLE V: Ablation study of the hybrid loss on BCI IV IIb and OpenBMI (%)

Dataset	Model	Acc $\pm$ std	Kappa $\pm$ std
BCI IV IIb	w/o DPA	80.03 $\pm$ 0.44	60.07 $\pm$ 0.87
	w/o Bank	77.65 $\pm$ 0.37	55.29 $\pm$ 0.75
	Whole	81.23 $\pm$ 0.11	61.99 $\pm$ 0.23
OpenBMI	w/o DPA	77.86 $\pm$ 0.35	55.72 $\pm$ 0.69
	w/o Bank	76.69 $\pm$ 0.19	53.37 $\pm$ 0.38
	Whole	78.94 $\pm$ 0.14	57.88 $\pm$ 0.28

TABLE VI: Ablation of DPA and memory bank (%)

Fig. 3: Effect of memory bank size on cross-subject accuracy.

Backbone	Baseline	MOPC	Parameters	FLOPs
EEGNet	76.28	81.23	2,060	2.87M
ConvNet	73.12	76.96	10,802	7.66M
LMDA	75.52	79.32	3,094	6.71M
Conformer	74.70	78.60	839,797	20.15M

TABLE VII: Performance and Computational Cost across Different Backbones

Fig. 4: t-SNE embeddings of BCI IV IIb features for (a) and (b) subjects B04 and (c) and (d) B06. (a) and (c) DT, while (b) and (d) effect of OTTA.

Method	Params updated (test)	Backprop / update	Cost vs. #cls.
Direct transfer	none	none	$\mathcal{O}(1)$
SHOT $\dagger$	feature encoder	multi-epoch	$\mathcal{O}(K)$
TENT	BN affine only	1	$\mathcal{O}(1)$
CoTTA $\ddagger$	full network	1	$\mathcal{O}(1)$
T-Time	full net, $\times M$	$M$	$\mathcal{O}(K)$
DPLOT	full network	2	$\mathcal{O}(1)$

TABLE VIII: Test-time computational profile of the adaptation methods, derived from each method’s design (backbone-independent)

Condition	Acc. (%)	$\kappa\ (\%)$	$\Delta$ vs. source
Source-only (static EA)	39.97	19.96	—
+ dynamic EA (no BN)	52.56	36.75	$+12.59$
MOPC (dynamic EA + BN)	55.05	39.73	$+15.08$

TABLE IX: Preliminary four-class decomposition on BCI IV 2a (single-seed, LOSO). MOPC is compared only against its own source-only and alignment-only ablations; no competing test-time-adaptation method is evaluated here

EEG Decoding

Electroencephalography (EEG) decoding maps brain-signal patterns to mental states, stimuli, speech, or intended actions.

See all 205 papers

Benchmarking Label-Revealed Online Updates for EEG BCI Decoding
Oct 5, 2026Bogdan Kozyrskiy, Artem Grachev, Abraham I. Camelo GuerreroBrain-Computer Interfaces EEG Decoding
Independent Researcher, France · Independent Researcher, Germany · School of Information Technology, York University, Toronto, Canada
Multi-Feature Riemannian Hypergraph for Online Test-Time Adaptation of Motor Imagery Brain-Computer Interface
Aug 17, 2026Siqi Li, Zhi Li, Tong Liu +5Cross-Session EEG Decoding MI Classification
Peking University · Chinese Institute for Brain Research, Beijing · NeuCyber Neurotech +2
PA-TCNet: Pathology-Aware Temporal Calibration with Physiology-Guided Target Refinement for Cross-Subject Motor Imagery EEG Decoding in Stroke Patients
Apr 17, 2026Xiangkai Wang, Yun Zhao, Dongyi He +5Cross-Subject EEG Decoding Brain-Computer Interfaces
School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401135, China; Chongqing Key Laboratory of Embodied Intelligence Perception and Autonomous Learning for Humanoid Robots; Key Laboratory of Advanced Equipment Intelligence of the Chongqing Education Commission, Chongqing 401135, China · School of Smart Health, Chongqing Polytechnic University of Electronic Technology, Chongqing 401131, China · Department of Language Science and Technology, The Hong Kong Polytechnic University, Hung Hom, Hong Kong SAR, China +2

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

Benchmarking Label-Revealed Online Updates for EEG BCI Decoding

Bogdan Kozyrskiy, Artem Grachev, Abraham I. Camelo Guerrero

Independent Researcher, France · Independent Researcher, Germany · School of Information Technology, York University, Toronto, Canada

Brain-Computer Interfaces EEG Decoding Online Continual Learning

Open paper AskPDF arXiv

Electroencephalography (EEG) signals drift over time, which can cause static brain-computer interface (BCI) models to degrade in practice. We present a benchmark for online adaptation and compare two widely used pipeline families, Common Spatial Patterns (CSP) and Riemannian covariance-based methods, under time-ordered prequential (test-then-train) evaluation. We examine (i) which pipelines benefit most from label-revealed updates, (ii) whether controlled forgetting of older data improves robustness, and (iii) how a minimal-calibration cold start compares with starting from a pretrained model. Across four datasets (three motor-imagery datasets and one movement-decoding dataset), label-revealed online updates improve 13 of 14 model/dataset pairs on the two largest streams, with relative accuracy gains of up to about 18% over a frozen model. A Shapley-based data-valuation analysis over temporal blocks assigns the largest mean value to the most recent block in each of the three analyzed datasets, while older blocks retain positive value.

Abstract

EEG Decoding

Explore similar work

Benchmarking Label-Revealed Online Updates for EEG BCI Decoding

Multi-Feature Riemannian Hypergraph for Online Test-Time Adaptation of Motor Imagery Brain-Computer Interface

PA-TCNet: Pathology-Aware Temporal Calibration with Physiology-Guided Target Refinement for Cross-Subject Motor Imagery EEG Decoding in Stroke Patients