Continual Learning for Flexible Collaboration in Medical Imaging: A Challenging Benchmark for Adapting to New Diseases and Imaging Domains

This work proposes a novel benchmark for evaluating continual learning methods in the context of multi-label medical image classification, combining the challenges of new class arrivals and domain shifts. To address these challenges, the authors introduce Pseudo-Label Replay, a method that integrates Pseudo-Labeling and Replay techniques to effectively handle new classes and domain shifts.