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

arXiv:2604.11091v1 Announce Type: new 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 extbf{L}ayer-importance guided extbf{D}ual extbf{E}xpandable extbf{P}rompt Pool (extbf{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.

Quantum-Gated Task-interaction Knowledge Distillation for Pre-trained Model-based Class-Incremental Learning
Visual Sparse Steering (VS2): Unsupervised Adaptation for Image Classification using Sparsity-Guided Steering Vectors
Near OOD Detection for Vision-Language Prompt Learning with Contrastive Logit Score
Person Re-Identification via Generalized Class Prototypes

Source: arXiv cs.CV | 2026-04-14

Related