paper-with-me

홈 › Papers

CARL-CXR: Continual Adapter-Based Routing for Task-Unknown Chest Radiograph Classification

2026-02-17 · Muthu Subash Kavitha, Anas Zafar, Amgad Muneer, Jia Wu arxiv

Clinical deployment of chest radiograph classifiers requires models that can be updated as new datasets become available without retraining on previously observed data or degrading validated performance. We study a task-incremental continual learning setting for chest radiograph classification under task-unknown inference, where heterogeneous chest X-ray datasets arrive sequentially and task identity is unavailable at deployment time. We propose CARL-CXR, a continual adapter-based routing framework that maintains a fixed high-capacity backbone while incrementally introducing lightweight task-specific adapters and classifier heads. A latent task selector operates on adapter-conditioned features to dynamically route each input to the most relevant task pathway, leveraging compact task prototypes and feature-level experience replay to preserve task identity across sequential updates without storing raw images. Experiments on MIMIC-CXR and CheXpert two large-scale datasets with distinct patient populations, imaging devices, and annotation pipelines demonstrate that CARL-CXR achieves minimal catastrophic forgetting (0.012 AUROC drop), representing a 6X and 11X reduction over established continual learning baselines LwF and EWC respectively, while maintaining competitive diagnostic performance (AUROC 0.74). Under task unknown deployment, CARL-CXR outperforms joint training by 12.5 points in routing accuracy (75.0% vs. 62.5%): unlike LwF and EWC, which require explicit task identifiers at inference and provide no routing mechanism.

📄 PDF Abstract BibTeX arXiv:2602.15811

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

Beyond Classification: Dynamic Adapter Routing for Continual Multimodal Retrieval

2026-05-29 · Alicja Dobrzeniecka, Filip Szatkowski, Sebastian Cygert, Szymon Lukasik 외 arxiv

While retrieval is a core function of vision-language models, continually updating these models for retrieval tasks remains critically underexplored. Existing work often approaches continual retrieval through the lens of…

class-incremental learning

Continual Model Routing in Evolving Model Hubs

2026-05-27 · Jack Bell, Giacomo Carfì, Gerlando Gramaglia, Vincenzo Lomonaco arxiv

AI model hubs provide access to a rapidly growing collection of powerful pre-trained models, enabling off-the-shelf mixture-of-experts systems with different routing strategies. However, this rapid growth poses two funda…

CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion

2026-01-14 · Ralf Römer, Yi Zhang, Yuming Li, Angela P. Schoellig arxiv

To teach robots complex manipulation tasks, a common approach is to fine-tune a pre-trained vision-language-action model (VLA) on task-specific data. However, since this recipe updates existing representations, it is uns…

Continual Learning

C-LoRA: Continual Low-Rank Adaptation for Pre-trained Models

2025-02-25 · Xin Zhang, Liang Bai, Xian Yang, Jiye Liang

Low-Rank Adaptation (LoRA) is an efficient fine-tuning method that has been extensively applied in areas such as natural language processing and computer vision. Existing LoRA fine-tuning approaches excel in static envir…

Continual Learning

DAM: Dynamic Adapter Merging for Continual Video QA Learning

2024-03-13 · Feng Cheng, Ziyang Wang, Yi-Lin Sung, Yan-Bo Lin 외

We present a parameter-efficient method for continual video question-answering (VidQA) learning. Our method, named DAM, uses the proposed Dynamic Adapter Merging to (i) mitigate catastrophic forgetting, (ii) enable effic…

Continual Learningimage-classificationImage ClassificationQuestion Answering+1