Paper Detail
Mai A. Shaaban, Tausifa Jan Saleem, Alaa Mohamed, Dilnaz Utemissova, Ufaq Khan, Mohammad Yaqub
Deploying medical visual question answering (MedVQA) systems in real-world clinical settings requires models that adapt to new clinical tasks without forgetting previously acquired knowledge. Continual learning (CL) provides a practical framework for this setting. Despite rapid progress in medical vision-language models, the behavior of CL methods when training these models across heterogeneous MedVQA tasks remains underexplored. This work presents a systematic evaluation of CL for MedVQA across diverse clinical objectives, including classification, multi-label classification, detection, cell counting, and report generation. Specifically, we explore (1) the ability of existing CL methods to mitigate catastrophic forgetting; (2) their sensitivity to task ordering, analyzing how different task sequences influence performance retention and forgetting; and (3) the evolution of low-rank adaptation parameters as new tasks are learned, revealing patterns of weight drift under different CL methods. Our findings suggest that existing CL methods struggle to maintain stability-plasticity balance when tasks with different objectives and supervision formats are interleaved. Code and full experimental setup will be publicly available.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{shaaban2026empirical,
title = {An Empirical Analysis of Continual Learning for Heterogeneous Medical Visual Question Answering},
author = {Mai A. Shaaban and Tausifa Jan Saleem and Alaa Mohamed and Dilnaz Utemissova and Ufaq Khan and Mohammad Yaqub},
year = {2026},
abstract = {Deploying medical visual question answering (MedVQA) systems in real-world clinical settings requires models that adapt to new clinical tasks without forgetting previously acquired knowledge. Continual learning (CL) provides a practical framework for this setting. Despite rapid progress in medical vision-language models, the behavior of CL methods when training these models across heterogeneous MedVQA tasks remains underexplored. This work presents a systematic evaluation of CL for MedVQA across},
url = {https://arxiv.org/abs/2607.12048},
keywords = {cs.CV, cs.AI, cs.CL},
eprint = {2607.12048},
archiveprefix = {arXiv},
}
{}