PEARL: Input-Agnostic Prompt Enhancement with Negative Feedback Regulation for Class-Incremental Learning

TL;DR

PEARL introduces an input-agnostic prompt enhancement method with negative feedback regulation to improve class-incremental learning, effectively reducing catastrophic forgetting and achieving state-of-the-art results across multiple benchmarks.

Contribution

The paper proposes a novel PTM-based CIL method called PEARL that uses input-agnostic prompts and negative feedback regulation to mitigate forgetting and enhance prompt adaptation.

Findings

Achieves state-of-the-art performance on six benchmarks.

Effectively reduces catastrophic forgetting in CIL.

Demonstrates robustness across diverse datasets.

Abstract

Class-incremental learning (CIL) aims to continuously introduce novel categories into a classification system without forgetting previously learned ones, thus adapting to evolving data distributions. Researchers are currently focusing on leveraging the rich semantic information of pre-trained models (PTMs) in CIL tasks. Prompt learning has been adopted in CIL for its ability to adjust data distribution to better align with pre-trained knowledge. This paper critically examines the limitations of existing methods from the perspective of prompt learning, which heavily rely on input information. To address this issue, we propose a novel PTM-based CIL method called Input-Agnostic Prompt Enhancement with Negative Feedback Regulation (PEARL). In PEARL, we implement an input-agnostic global prompt coupled with an adaptive momentum update strategy to reduce the model's dependency on data distribution, thereby effectively mitigating catastrophic forgetting. Guided by negative feedback regulation, this adaptive momentum update addresses the parameter sensitivity inherent in fixed-weight momentum updates. Furthermore, it fosters the continuous enhancement of the prompt for new tasks by harnessing correlations between different tasks in CIL. Experiments on six benchmarks demonstrate that our method achieves state-of-the-art performance. The code is available at: https://github.com/qinyongchun/PEARL.