Convolutional Prompting meets Language Models for Continual Learning

arXiv:2403.20317v1 Announce Type: new
Abstract: Continual Learning (CL) enables machine learning models to learn from continuously shifting new training data in absence of data from old tasks. Recently, pretrained vision transformers combined with prompt tuning have shown promise for overcoming catastrophic forgetting in CL. These approaches rely on a pool of learnable prompts which can be inefficient in sharing knowledge across tasks leading to inferior performance. In addition, the lack of fine-grained layer specific prompts does not allow these to …

abstract arxiv catastrophic forgetting continual cs.cv data language language models learn machine machine learning machine learning models pool prompt prompting prompt tuning tasks training training data transformers type vision vision transformers