Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

12-2022

Abstract

State-of-the-art deep neural networks are still struggling to address the catastrophic forgetting problem in continual learning. In this paper, we propose one simple paradigm (named as S-Prompting) and two concrete approaches to highly reduce the forgetting degree in one of the most typical continual learning scenarios, i.e., domain increment learning (DIL). The key idea of the paradigm is to learn prompts independently across domains with pre-trained transformers, avoiding the use of exemplars that commonly appear in conventional methods. This results in a win-win game where the prompting can achieve the best for each domain. The independent prompting across domains only requests one single cross-entropy loss for training and one simple K-NN operation as a domain identifier for inference. The learning paradigm derives an image prompt learning approach and a novel language-image prompt learning approach. Owning an excellent scalability (0.03% parameter increase per domain), the best of our approaches achieves a remarkable relative improvement (an average of about 30%) over the best of the state-of-the-art exemplar-free methods for three standard DIL tasks, and even surpasses the best of them relatively by about 6% in average when they use exemplars. Source code is available at https://github.com/iamwangyabin/S-Prompts.

Keywords

Prompts Learning, Pre-trained Transformers, Occam's Razor, Domain Incremental Learning

Discipline

Artificial Intelligence and Robotics | Databases and Information Systems

Research Areas

Intelligent Systems and Optimization

Publication

Proceedings of the 36th Conference on Neural Information Processing Systems, New Orleans, United States, 2022 November 28 - December 9

First Page

1

Last Page

24

Publisher

Curran Associates

City or Country

New Orleans

Download

Share

COinS