Recent rehearsal-free continual learning (CL) methods guided by prompts achieve strong performance on vision tasks with non-stationary data but remain resourceintensive, hindering real-world edge deployment. We introduce resource-efficient prompting (REP), which improves the computational and memory efficiency of prompt-based rehearsal-free continual learning methods while minimizing accuracy trade-offs. Our approach employs swift prompt selection to refine input data using a carefully provisioned model and introduces adaptive token merging (AToM) and adaptive layer dropping (ALD) for efficient prompt updates. AToM and ALD selectively skip data and model layers while preserving task-specific features during the learning of new tasks. Extensive experiments on multiple image classification datasets demonstrate REP’s superior resource efficiency over state-of-the-art rehearsal-free CL methods.
- Ubuntu 18.04 LTS
- NVIDIA RTX 3090
- Python 3.8.8
pytorch==1.12.1 + CUDA 11.3
torchvision==0.13.1
timm==0.6.7
pillow==9.2.0
matplotlib==3.5.3
@inproceedings{
jeon2025rep,
title={REP: Resource-Efficient Prompting for Rehearsal-Free Continual Learning},
author={Sungho Jeon and Xinyue Ma and Kwang In Kim and Myeongjae Jeon},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
}