Towards Robust Visual Continual Learning with Multi-Prototype Supervision
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909797878595584 |
|---|---|
| author | Liu, Xiwei Li, Yulong Li, Yichen Zhuang, Xinlin Yang, Haolin Li, Huifa Razzak, Imran |
| author_facet | Liu, Xiwei Li, Yulong Li, Yichen Zhuang, Xinlin Yang, Haolin Li, Huifa Razzak, Imran |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_16011 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Robust Visual Continual Learning with Multi-Prototype Supervision Liu, Xiwei Li, Yulong Li, Yichen Zhuang, Xinlin Yang, Haolin Li, Huifa Razzak, Imran Computer Vision and Pattern Recognition 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. |
| title | Towards Robust Visual Continual Learning with Multi-Prototype Supervision |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.16011 |