Rehearsal-free and Task-free Online Continual Learning With Contrastive Prompt
This addresses data security and privacy concerns in continual learning by eliminating the need for rehearsal buffers and task identities, though it is incremental as it builds on existing prompt learning and NCM classifier techniques.
The paper tackled catastrophic forgetting in online continual learning by proposing a rehearsal-free and task-free method that integrates prompt learning with an NCM classifier, achieving effective results on two benchmarks without storing samples or using task boundaries.
The main challenge of continual learning is \textit{catastrophic forgetting}. Because of processing data in one pass, online continual learning (OCL) is one of the most difficult continual learning scenarios. To address catastrophic forgetting in OCL, some existing studies use a rehearsal buffer to store samples and replay them in the later learning process, other studies do not store samples but assume a sequence of learning tasks so that the task identities can be explored. However, storing samples may raise data security or privacy concerns and it is not always possible to identify the boundaries between learning tasks in one pass of data processing. It motivates us to investigate rehearsal-free and task-free OCL (F2OCL). By integrating prompt learning with an NCM classifier, this study has effectively tackled catastrophic forgetting without storing samples and without usage of task boundaries or identities. The extensive experimental results on two benchmarks have demonstrated the effectiveness of the proposed method.