Leveraging Old Knowledge to Continually Learn New Classes in Medical Images
This addresses the problem of continuously learning new disease classes without forgetting old ones for medical AI systems, representing an incremental improvement in a domain-specific context.
The paper tackles class-incremental continual learning in medical images by proposing a framework with dynamic architecture and alternating training to prevent catastrophic forgetting, achieving superior performance over state-of-the-art baselines in accuracy and forgetting metrics.
Class-incremental continual learning is a core step towards developing artificial intelligence systems that can continuously adapt to changes in the environment by learning new concepts without forgetting those previously learned. This is especially needed in the medical domain where continually learning from new incoming data is required to classify an expanded set of diseases. In this work, we focus on how old knowledge can be leveraged to learn new classes without catastrophic forgetting. We propose a framework that comprises of two main components: (1) a dynamic architecture with expanding representations to preserve previously learned features and accommodate new features; and (2) a training procedure alternating between two objectives to balance the learning of new features while maintaining the model's performance on old classes. Experiment results on multiple medical datasets show that our solution is able to achieve superior performance over state-of-the-art baselines in terms of class accuracy and forgetting.