Paper Detail

MOSAIC: Modality-Specific Adaptation for Incremental Continual Learning in Parkinson's Disease Gait Assessment

Minlin Zeng, Zhipeng Zhou, Yang Qiu, Martin J. McKeown, Zhiqi Shen

arxiv Score 15.0

Published 2026-06-11 · First seen 2026-06-13

Research Track A · General AI

Abstract

Gait-based Parkinson's disease assessment increasingly relies on heterogeneous sensors, but clinical systems rarely collect all modalities simultaneously. New sensors may arrive through device upgrades, protocol changes, or multi-center deployment, while historical patient data are often unavailable because of privacy and storage constraints. This modality-incremental setting faces three challenges: unreliable cross-modal distillation, modality-specific statistical shifts, and reduced plasticity after preservation. We propose MOSAIC, a compact continual learning framework. First, we identify the Toxic Teacher phenomenon and introduce Modality-Specific Warm-Up to stabilize newly learned modality representations before distillation. Second, we propose a statistics-decoupled MSBN architecture that isolates sensor statistics while maintaining a shared semantic backbone. Third, we design a curriculum-guided repulsive objective for Plasticity Recovery, preserving legacy knowledge while recovering modality-specific capacity. Experiments on three multimodal Parkinson's gait datasets show that MOSAIC improves final performance and mitigates forgetting. Project code is available at: https://github.com/minlinzeng/MOSAIC_Modality-Specific-Adaptation-for-Incremental-Continual-Learning-in-PD-Gait-Assessment.git

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{zeng2026mosaic,
  title = {MOSAIC: Modality-Specific Adaptation for Incremental Continual Learning in Parkinson's Disease Gait Assessment},
  author = {Minlin Zeng and Zhipeng Zhou and Yang Qiu and Martin J. McKeown and Zhiqi Shen},
  year = {2026},
  abstract = {Gait-based Parkinson's disease assessment increasingly relies on heterogeneous sensors, but clinical systems rarely collect all modalities simultaneously. New sensors may arrive through device upgrades, protocol changes, or multi-center deployment, while historical patient data are often unavailable because of privacy and storage constraints. This modality-incremental setting faces three challenges: unreliable cross-modal distillation, modality-specific statistical shifts, and reduced plasticity},
  url = {https://arxiv.org/abs/2606.13258},
  keywords = {cs.AI},
  eprint = {2606.13258},
  archiveprefix = {arXiv},
}

Metadata

{}