LDEPrompt: Layer-importance guided Dual Expandable Prompt Pool for Pre-trained Model-based Class-Incremental Learning

TL;DR

LDEPrompt introduces an adaptive, layer-importance guided dual expandable prompt pool for improved class-incremental learning with pre-trained models, achieving state-of-the-art results.

Contribution

It proposes a novel prompt pool mechanism that dynamically expands and adapts layers, overcoming fixed prompt limitations and enhancing scalability.

Findings

LDEPrompt outperforms existing methods on standard benchmarks.

The adaptive prompt pool improves scalability and performance.

Experiments validate the effectiveness of layer-guided expansion.

Abstract

Prompt-based class-incremental learning methods typically construct a prompt pool consisting of multiple trainable key-prompts and perform instance-level matching to select the most suitable prompt embeddings, which has shown promising results. However, existing approaches face several limitations, including fixed prompt pools, manual selection of prompt embeddings, and strong reliance on the pretrained backbone for prompt selection. To address these issues, we propose a \textbf{L}ayer-importance guided \textbf{D}ual \textbf{E}xpandable \textbf{P}rompt Pool (\textbf{LDEPrompt}), which enables adaptive layer selection as well as dynamic freezing and expansion of the prompt pool. Extensive experiments on widely used class-incremental learning benchmarks demonstrate that LDEPrompt achieves state-of-the-art performance, validating its effectiveness and scalability.