Prompt Customization for Continual Learning

arXiv:2404.18060v1 Announce Type: cross
Abstract: Contemporary continual learning approaches typically select prompts from a pool, which function as supplementary inputs to a pre-trained model. However, this strategy is hindered by the inherent noise of its selection approach when handling increasing tasks. In response to these challenges, we reformulate the prompting approach for continual learning and propose the prompt customization (PC) method. PC mainly comprises a prompt generation module (PGM) and a prompt modulation module (PMM). In contrast to conventional methods …

abstract arxiv challenges continual cs.cv cs.lg customization function however inputs noise pool pre-trained model prompt prompting prompts strategy tasks type