Learning to Prompt Knowledge Transfer for Open-World Continual Learning
This work addresses the challenge of continual learning in open-world scenarios, which is important for AI systems that need to adapt to new data over time, though it appears incremental as it builds on existing OwCL methods.
The paper tackles the problem of Open-world Continual Learning (OwCL), which involves learning new tasks without forgetting past knowledge and identifying novel objects, by proposing Pro-KT, a prompt-enhanced knowledge transfer model. Experimental results show that Pro-KT outperforms state-of-the-art methods in detecting unknowns and classifying knowns on two real-world datasets.
This paper studies the problem of continual learning in an open-world scenario, referred to as Open-world Continual Learning (OwCL). OwCL is increasingly rising while it is highly challenging in two-fold: i) learning a sequence of tasks without forgetting knowns in the past, and ii) identifying unknowns (novel objects/classes) in the future. Existing OwCL methods suffer from the adaptability of task-aware boundaries between knowns and unknowns, and do not consider the mechanism of knowledge transfer. In this work, we propose Pro-KT, a novel prompt-enhanced knowledge transfer model for OwCL. Pro-KT includes two key components: (1) a prompt bank to encode and transfer both task-generic and task-specific knowledge, and (2) a task-aware open-set boundary to identify unknowns in the new tasks. Experimental results using two real-world datasets demonstrate that the proposed Pro-KT outperforms the state-of-the-art counterparts in both the detection of unknowns and the classification of knowns markedly.