KOPPA: Improving Prompt-based Continual Learning with Key-Query Orthogonal Projection and Prototype-based One-Versus-All
This work improves continual learning for vision tasks, offering a significant performance gain over existing methods, though it is incremental in nature.
The paper tackles the problem of prompt-based continual learning in pre-trained ViT networks by addressing limitations in key-query matching and feature shifts, resulting in a method that surpasses current state-of-the-art approaches by up to 20% on benchmark datasets.
Drawing inspiration from prompt tuning techniques applied to Large Language Models, recent methods based on pre-trained ViT networks have achieved remarkable results in the field of Continual Learning. Specifically, these approaches propose to maintain a set of prompts and allocate a subset of them to learn each task using a key-query matching strategy. However, they may encounter limitations when lacking control over the correlations between old task queries and keys of future tasks, the shift of features in the latent space, and the relative separation of latent vectors learned in independent tasks. In this work, we introduce a novel key-query learning strategy based on orthogonal projection, inspired by model-agnostic meta-learning, to enhance prompt matching efficiency and address the challenge of shifting features. Furthermore, we introduce a One-Versus-All (OVA) prototype-based component that enhances the classification head distinction. Experimental results on benchmark datasets demonstrate that our method empowers the model to achieve results surpassing those of current state-of-the-art approaches by a large margin of up to 20%.