Hai-Long Sun @ LAMDA, NJU-AI

M.Sc. Student, LAMDA Group
School of Artificial Intelligence
National Key Laboratory for Novel Software Technology
Nanjing University, Nanjing 210023, China

Supervisor: Han-Jia Ye(叶翰嘉)

Laboratory: Yifu Building, Xianlin Campus of Nanjing University

Email: sunhl@lamda.nju.edu.cn

• Hai-Long Sun, Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan. PILOT: A Pre-Trained Model-Based Continual Learning Toolbox. arXiv:2309.07117, 2023. [Paper] [Code] [中文解读]

We introduces PILOT, a pre-trained model-based continual learning toolbox. On the one hand, PILOT implements some state-of-the-art class-incremental learning algorithms based on pre-trained models, such as L2P, DualPrompt, and CODA-Prompt. On the other hand, PILOT also fits typical class-incremental learning algorithms (e.g., DER, FOSTER, and MEMO) within the context of pre-trained models to evaluate their effectiveness.

• Da-Wei Zhou, Hai-Long Sun, Han-Jia Ye, De-Chuan Zhan. Continual Learning with Pre-Trained Models: A Survey. arXiv:2401.16386, 2024. [Paper] [Code] [中文解读]

We presents a comprehensive survey of the latest advancements in PTM-based CL. We categorize existing methodologies into three distinct groups, providing a comparative analysis of their similarities, differences, and respective advantages and disadvantages. Additionally, we offer an empirical study contrasting various state-of-the-art methods to highlight concerns regarding fairness in comparisons.

• Da-Wei Zhou, Hai-Long Sun, Han-Jia Ye, De-Chuan Zhan. Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning. The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'24). [Paper] [Code]

We propose Expandable Subspace Ensemble (EASE) for PTM-based CIL. To enable model updating without conflict, we train a distinct lightweight adapter module for each new task, aiming to create task-specific subspaces. These adapters span a high-dimensional feature space, enabling joint decision-making across multiple subspaces. As data evolves, the expanding subspaces render the old class classifiers incompatible with new-stage spaces. Correspondingly, we design a semantic-guided prototype complement strategy that synthesizes old classes’ new features without using any old class instance.