Towards Robust Visual Continual Learning with Multi-Prototype Supervision
Liu, Xiwei Li, Yulong Li, Yichen Zhuang, Xinlin Yang, Haolin Li, Huifa Razzak, Imran
Liu, Xiwei
Li, Yulong
Li, Yichen
Zhuang, Xinlin
Yang, Haolin
Li, Huifa
Razzak, Imran
Supervisor
Department
Computational Biology
Embargo End Date
Type
Conference proceeding
Date
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Language-guided supervision, which utilizes a frozen semantic target from a Pretrained Language Model (PLM), has emerged as a promising paradigm for visual Continual Learning (CL). However, relying on a single target introduces two critical limitations: 1) semantic ambiguity, where a polysemous category name results in conflicting visual representations, and 2) intra-class visual diversity, where a single prototype fails to capture the rich variety of visual appearances within a class. To this end, we propose MuproCL, a novel framework that replaces the single target with multiple, context-aware prototypes. Specifically, we employ a lightweight LLM agent to perform category disambiguation and visual-modal expansion to generate a robust set of semantic prototypes. A LogSumExp aggregation mechanism allows the vision model to adaptively align with the most relevant prototype for a given image. Extensive experiments across various CL baselines demonstrate that MuproCL consistently enhances performance and robustness, establishing a more effective path for language-guided continual learning.
Citation
X. Liu, Y. Li, Y. Li, X. Zhuang, H. Yang, H. Li , et al., "Towards Robust Visual Continual Learning with Multi-Prototype Supervision," 2026, pp. 8867-8871.
Source
ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Conference
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Keywords
46 Information and Computing Sciences, 4611 Machine Learning
Subjects
Source
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher
IEEE