Abstract
Benefiting from transferable visual-textual alignment, CLIP has been widely adopted for class-incremental learning (CIL). However, existing learners either repeatedly update components shared across tasks, leading to knowledge overwriting, or overly isolate new-task updates, hindering the reuse of CLIP's transferable knowledge and limiting plasticity. Moreover, the text-based or bimodal classifier designs still fail to effectively integrate complementary information from the visual and textual modalities. To address these challenges, we introduce DuLBE, which couples dual-mode low-rank learning with a bridge-prototype ensemble classifier for exemplar-free CIL. DuLBE allocates two visual low-rank update modes according to the gradient demand and uses gradient routing to coordinate them: a compact and rewritable shared mode is selected from historically occupied visual directions to reuse transferable knowledge, while residual modes provide low-interference channels for task-specific variations. Building on the resulting stable inter-modal structure, we further construct geodesic bridges between visual prototypes and text embeddings on the unit hypersphere, and ensemble reliable bridge prototypes to compensate for the modality-gap limitations of textual decision boundaries. Extensive experiments under multiple settings show that DuLBE achieves state-of-the-art CIL performance while retaining the high parameter efficiency of low-rank tuning.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
He, C., Qiu, Z., Meng, F., Wang, C., Chen, L., Xu, L., Wu, Q., & Li, H. (2026). Dual-Mode Low-Rank Learner with Bridge-Prototype Ensemble for Vision-Language Class-Incremental Learning. https://omanscience.com/en/articles/dual-mode-low-rank-learner-with-bridge-prototype-ensemble-for-vision-language-class-incremental-learning
MLA 9
He, Chiyuan, et al. "Dual-Mode Low-Rank Learner with Bridge-Prototype Ensemble for Vision-Language Class-Incremental Learning." https://omanscience.com/en/articles/dual-mode-low-rank-learner-with-bridge-prototype-ensemble-for-vision-language-class-incremental-learning.
Chicago (author–date)
He, Chiyuan, Zihuan Qiu, Fanman Meng, Chao Wang, Liangjiang Chen, Linfeng Xu, Qingbo Wu, and Hongliang Li. 2026. "Dual-Mode Low-Rank Learner with Bridge-Prototype Ensemble for Vision-Language Class-Incremental Learning." https://omanscience.com/en/articles/dual-mode-low-rank-learner-with-bridge-prototype-ensemble-for-vision-language-class-incremental-learning.
Harvard
He, C., Qiu, Z., Meng, F., Wang, C., Chen, L., Xu, L., Wu, Q. and Li, H. (2026) 'Dual-Mode Low-Rank Learner with Bridge-Prototype Ensemble for Vision-Language Class-Incremental Learning', Available at: https://omanscience.com/en/articles/dual-mode-low-rank-learner-with-bridge-prototype-ensemble-for-vision-language-class-incremental-learning.
Vancouver
He C, Qiu Z, Meng F, Wang C, Chen L, Xu L, et al. Dual-Mode Low-Rank Learner with Bridge-Prototype Ensemble for Vision-Language Class-Incremental Learning. https://omanscience.com/en/articles/dual-mode-low-rank-learner-with-bridge-prototype-ensemble-for-vision-language-class-incremental-learning
IEEE
C. He, Z. Qiu, F. Meng, C. Wang, L. Chen, L. Xu, Q. Wu, and H. Li, "Dual-Mode Low-Rank Learner with Bridge-Prototype Ensemble for Vision-Language Class-Incremental Learning," https://omanscience.com/en/articles/dual-mode-low-rank-learner-with-bridge-prototype-ensemble-for-vision-language-class-incremental-learning.