Unsupervised cross-domain adaptation for wearable-based human activity recognition

Abstract Recent advancements in deep learning-based wearable human action recognition (wHAR) have improved the capture and classification of complex motions. Still, adoption remains limited due to the lack of expert annotations and domain discrepancies from user variations. Limited annotations hinder the model’s ability to generalize to out-of-distribution samples. While data augmentation can improve generalizability, unsupervised augmentation techniques must be applied carefully to avoid introducing noise. Unsupervised domain adaptation (UDA) addresses domain discrepancies by aligning conditional distributions with labeled target samples, but vanilla pseudo-labeling can lead to error propagation. To address these challenges, we propose CoHAR , a novel joint optimization architecture comprised of three functions: (i) consistency regularizer between augmented samples to improve model classification generalizability, (ii) temporal ensemble for robust pseudo-label generation, and (iii) conditional distribution alignment to improve domain generalizability. The temporal ensemble works by aggregating predictions from past epochs to smooth out noisy pseudo-label predictions, which are then used in the conditional distribution alignment module to minimize kernel-based class-wise conditional maximum mean discrepancy ( k CMMD) between the source and target feature space to learn a domain-invariant embedding. The consistency-regularized augmentations ensure that multiple augmentations of the same sample share the same labels; this results in (a) strong generalization with limited source domain samples and (b) consistent pseudo-label generation in target samples. The novel integration of these three modules in CoHAR results in a range of $$\varvec{\approx } {\varvec{4}}--{\varvec{12\%}}$$ ≈ 4 - - 12 % average macro-F1 score improvement over six state-of-the-art UDA methods in five benchmark wHAR datasets.

Authors

Institutions

Publication Details

Journal
Knowledge and Information Systems
Published
2026-11-17
DOI
https://doi.org/10.1007/s10115-026-02918-8
Primary Topic
Domain Adaptation and Few-Shot Learning
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Unsupervised cross-domain adaptation for wearable-based human activity recognition

Indrajeet Ghosh, Garvit Chugh, Nirmalya Roy, Abu Zaher Md Faridee
3 links
Knowledge and Information Systems
Domain Adaptation and Few-Shot Learning
article

Unsupervised cross-domain adaptation for wearable-based human activity recognition

Indrajeet Ghosh, Garvit Chugh, Nirmalya Roy, Abu Zaher Md Faridee
article en

Abstract

Abstract Recent advancements in deep learning-based wearable human action recognition (wHAR) have improved the capture and classification of complex motions. Still, adoption remains limited due to the lack of expert annotations and domain discrepancies from user variations. Limited annotations hinder the model’s ability to generalize to out-of-distribution samples. While data augmentation can improve generalizability, unsupervised augmentation techniques must be applied carefully to avoid introducing noise. Unsupervised domain adaptation (UDA) addresses domain discrepancies by aligning conditional distributions with labeled target samples, but vanilla pseudo-labeling can lead to error propagation. To address these challenges, we propose CoHAR , a novel joint optimization architecture comprised of three functions: (i) consistency regularizer between augmented samples to improve model classification generalizability, (ii) temporal ensemble for robust pseudo-label generation, and (iii) conditional distribution alignment to improve domain generalizability. The temporal ensemble works by aggregating predictions from past epochs to smooth out noisy pseudo-label predictions, which are then used in the conditional distribution alignment module to minimize kernel-based class-wise conditional maximum mean discrepancy ( k CMMD) between the source and target feature space to learn a domain-invariant embedding. The consistency-regularized augmentations ensure that multiple augmentations of the same sample share the same labels; this results in (a) strong generalization with limited source domain samples and (b) consistent pseudo-label generation in target samples. The novel integration of these three modules in CoHAR results in a range of $$\varvec{\approx } {\varvec{4}}--{\varvec{12\%}}$$ ≈ 4 - - 12 % average macro-F1 score improvement over six state-of-the-art UDA methods in five benchmark wHAR datasets.

Knowledge and Information SystemsVol. 68(1)
Amazon (United States) (US), Indian Institute of Technology Jodhpur (IN), University of Virginia (US), University of Maryland, Baltimore County (US)
National Science Foundation, U.S. Department of Defense, Office of Naval Research
Domain Adaptation and Few-Shot Learning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon