PromptFusion: Decoupling Stability and Plasticity for Continual Learning
Current research on continual learning mainly focuses on relieving catastrophic forgetting, and most of their success is at the cost of limiting the performance of newly incoming tasks. Such a trade-off is referred to as the stability-plasticity dilemma and is a more general and challenging problem for continual learning. However, the inherent conflict between these two concepts makes it seemingly impossible to devise a satisfactory solution to both of them simultaneously. Therefore, we ask, "is it possible to divide them into two separate problems to conquer them independently?". To this end, we propose a prompt-tuning-based method termed PromptFusion to enable the decoupling of stability and plasticity. Specifically, PromptFusion consists of a carefully designed \stab module that deals with catastrophic forgetting and a \boo module to learn new knowledge concurrently. Furthermore, to address the computational overhead brought by the additional architecture, we propose PromptFusion-Lite which improves PromptFusion by dynamically determining whether to activate both modules for each input image. Extensive experiments show that both PromptFusion and PromptFusion-Lite achieve promising results on popular continual learning datasets for class-incremental and domain-incremental settings. Especially on Split-Imagenet-R, one of the most challenging datasets for class-incremental learning, our method can exceed state-of-the-art prompt-based methods by more than 5\% in accuracy, with PromptFusion-Lite using 14.8\% less computational resources than PromptFusion.
Code (1)
Tasks
class-incremental learningClass Incremental LearningContinual LearningIncremental LearningSimilar Papers 제목 키워드 기반
Loss Decoupling for Task-Agnostic Continual Learning
Continual learning requires the model to learn multiple tasks in a sequential order. To perform continual learning, the model must possess the abilities to maintain performance on old tasks (stability) and adapt itself t…
Rethinking Gradient Projection Continual Learning: Stability / Plasticity Feature Space Decoupling
Continual learning aims to incrementally learn novel classes over time, while not forgetting the learned knowledge. Recent studies have found that learning would not forget if the updated gradient is orthogonal to th…
Continual LearningNew Insights for the Stability-Plasticity Dilemma in Online Continual Learning
The aim of continual learning is to learn new tasks continuously (i.e., plasticity) without forgetting previously learned knowledge from old tasks (i.e., stability). In the scenario of online continual learning, wherein …
Continual LearningForgetting, plasticity, and co-observation: a third facet of continual learning
Efficient continual learning remains a fundamental challenge for deep neural networks. While catastrophic forgetting and loss of plasticity are widely considered the primary obstacles to overcome, we show that these two …
Continual LearningA Plasticity-Aware Method for Continual Self-Supervised Learning in Remote Sensing
Continual self-supervised learning (CSSL) methods have gained increasing attention in remote sensing (RS) due to their capability to learn new tasks sequentially from continuous streams of unlabeled data. Existing CSSL m…
Continual Self-Supervised LearningKnowledge DistillationSelf-Supervised Learning