DPFormer: Dynamic Prompt Transformer for Continual Learning

TL;DR

DPFormer introduces a dynamic prompt transformer that effectively addresses catastrophic forgetting and inter-task confusion in continual learning by using prompt schemes to retain knowledge and distinguish tasks within a single model.

Contribution

The paper proposes a novel dynamic prompt transformer with prompt schemes that enable continual learning with fixed model parameters and improved task differentiation.

Findings

Achieves state-of-the-art performance on CIFAR-100, ImageNet100, and ImageNet1K datasets.

Effectively mitigates catastrophic forgetting and inter-task confusion.

Provides a unified, end-to-end trainable model for continual learning.

Abstract

In continual learning, solving the catastrophic forgetting problem may make the models fall into the stability-plasticity dilemma. Moreover, inter-task confusion will also occur due to the lack of knowledge exchanges between different tasks. In order to solve the aforementioned problems, we propose a novel dynamic prompt transformer (DPFormer) with prompt schemes. The prompt schemes help the DPFormer memorize learned knowledge of previous classes and tasks, and keep on learning new knowledge from new classes and tasks under a single network structure with a nearly fixed number of model parameters. Moreover, they also provide discrepant information to represent different tasks to solve the inter-task confusion problem. Based on prompt schemes, a unified classification module with the binary cross entropy loss, the knowledge distillation loss and the auxiliary loss is proposed to train the whole model in an end-to-end trainable manner. Compared with state-of-the-art methods, our method achieves the best performance in the CIFAR-100, ImageNet100 and ImageNet1K datasets under different class-incremental settings in continual learning. The source code will be available at our GitHub after acceptance.