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

Linjie Li; Zhenyu Wu; Huiyu Xiao; Yang Ji

cs.CVApr 13, 2026

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

Authors: Linjie Li, Zhenyu Wu, Huiyu Xiao, Yang Ji

Organizations: School of Information and Communication Engineering, BUPT. · Engineering Research Center for Information Network, Ministry of Education

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 Layer-importance guided Dual Expandable Prompt Pool (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.

Figures & tables

Figure 1: Illustration of LDEPrompt. The upper part (from left to right) shows: (1) the forward-pass evaluation of layer importance before training; (2) task-specific prompt retrieval from the global prompt pool at layer $K$ using the CLS token; and (3) the construction of a layer-specific prompt pool of size $n$ , where selected prompts are frozen while newly initialized prompts remain trainable;(4) During training, prompts within each layer are merged to form the final task-specific representations.

Method	CIFAR B0-Inc10		CUB B0-Inc20		VTAB B0-Inc10
Method	Avg( $\uparrow$ )	Last( $\uparrow$ )	Avg( $\uparrow$ )	Last( $\uparrow$ )	Avg( $\uparrow$ )	Last( $\uparrow$ )
L2P [ 17 ]	88.83 ± 1.39	83.46 ± 2.00	77.21 ± 0.91	68.22 ± 0.84	78.71 ± 6.22	60.57 ± 7.60
Dualprompt [ 16 ]	89.39 ± 1.12	84.58 ± 0.77	84.18 ± 0.49	74.27 ± 0.49	88.59 ± 2.28	77.64 ± 3.33
CODA-Prompt [ 12 ]	90.60 ± 0.33	87.01 ± 0.19	83.89 ± 1.52	75.33 ± 1.06	88.16 ± 2.10	76.80 ± 2.69
Aper-VPT-S [ 19 ]	85.20 ± 0.43	79.77 ± 0.45	90.21 ± 1.42	86.23 ± 0.21	91.21 ± 0.46	83.78 ± 0.60
Aper-VPT-D [ 19 ]	86.26 ± 0.79	80.28 ± 0.87	90.06 ± 1.35	86.12 ± 0.11	91.23 ± 0.62	83.70 ± 1.39

Table 1: Average and final accuracy comparison across three datasets. Bold numbers indicate the best performance, while underlined values represent the second-best. All methods are evaluated under the exemplar-free setting.

Panel of Figure 2 — Figure 2: Performance curve of various methods under different settings.

#	CIFAR B0-Inc10	CUB B0-Inc20	VTAB B0-Inc10
(1)	88.23	87.23	85.34
(2)	89.03	89.42	90.12
(3)	91.56	91.91	92.87
(4)	92.00	92.55	94.55

Table 2: Ablation results(Avg) for each component.

Class-Incremental Learning

Class-incremental learning studies how models can add new categories over time while retaining the ability to recognize previously learned classes.

See all 160 papers

Dynamic LoRA-Experts and Prototype-Ensemble Matching for Class-Incremental Learning
Sep 30, 2026Hongwei Zhao, Rui Liu, Yansong LiuClass-Incremental Learning Prototype-Based Classification
School of Computer Science and Engineering, Beihang University
Beyond Prompt Degradation: Prototype-guided Dual-pool Prompting for Incremental Object Detection
Mar 2, 2026Yaoteng Zhang, Zhou Qing, Junyu Gao +1Object Detection Class-Incremental Learning
Northwestern Polytechnical University
Information-Theoretic Decoupled Prompt Tuning for Continual Learning
Aug 13, 2026Yunfei Zhang, Wen Wen, Tieliang Gong +1Continual Learning for VLMs Continual Learning for LLMs
National Engineering Lab for Big Data Analytics, School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710049, China

Sep 30, 2026J/K move · Enter open · S save

Dynamic LoRA-Experts and Prototype-Ensemble Matching for Class-Incremental Learning

Hongwei Zhao, Rui Liu, Yansong Liu

School of Computer Science and Engineering, Beihang University

Class-Incremental Learning Prototype-Based Classification Continual Learning Low-Rank Adaptation Parameter-Efficient Fine-Tuning

Open paper AskPDF arXiv

Class-Incremental Learning (CIL) aims to continuously learn new classes without forgetting previously acquired knowledge. Parameter-efficient fine-tuning with pre-trained models reduces parameter overhead but can suffer from cumulative interference and suboptimal alignment between inference samples and specialized modules. We propose Dynamic LoRA-Experts and Prototype-Ensemble Matching (DLEPEM), a two-stage rehearsal-free framework. DLEPEM allocates a task-specific LoRA-Expert for each incremental task to reduce cross-task interference, then combines frozen pre-trained-model prototypes with task-adaptive LoRA-Expert prototypes for reliable task-level discrimination. Experiments on standard CIL and Few-Shot CIL benchmarks demonstrate strong performance under the evaluated protocols.

Abstract

Class-Incremental Learning

Explore similar work

Dynamic LoRA-Experts and Prototype-Ensemble Matching for Class-Incremental Learning

Beyond Prompt Degradation: Prototype-guided Dual-pool Prompting for Incremental Object Detection

Information-Theoretic Decoupled Prompt Tuning for Continual Learning