Rehearsal-Based Continual Learning with Dual Prompts

Academic Background In the fields of machine learning and neural networks, continual learning is an important research direction. The goal of continual learning is to enable models to continuously learn new knowledge across a series of tasks while avoiding forgetting previously acquired knowledge. However, existing continual learning methods face a...

Federated Learning Using Model Projection for Multi-Center Disease Diagnosis with Non-IID Data

Federated Learning Using Model Projection for Multi-Center Disease Diagnosis with Non-IID Data

Federated Learning Using Model Projection for Multi-Center Disease Diagnosis Background Introduction With the rapid development of medical imaging technology, research on automated diagnostic methods has shown good performance on single-center datasets. However, these methods often find it difficult to generalize to data from other healthcare facil...