Metraipolis › archive › dc_f1ef44be8fcb
Dual-Mode Low-Rank Learner with Bridge-Prototype Ensemble for Vision-Language Class-Incremental Learning — arXiv:2609.36759
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36759
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:26:21.300Z
- SHA-256 of the archived text
fe2399cc52783b2b581594c550c915ce0aaab05052eaaa7ed475e522355b10b1- Stable URL of this page
https://metraipolis.com/documento/dc_f1ef44be8fcb
How to cite
Dual-Mode Low-Rank Learner with Bridge-Prototype Ensemble for Vision-Language Class-Incremental Learning — arXiv:2609.36759 — arXiv (en), https://arxiv.org/abs/2609.36759 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f1ef44be8fcb (Metraipolis archive dc_f1ef44be8fcb, sha256 fe2399cc52783b2b581594c550c915ce0aaab05052eaaa7ed475e522355b10b1)
BibTeX
@misc{dcf1ef44be8fcb,
title = {Dual-Mode Low-Rank Learner with Bridge-Prototype Ensemble for Vision-Language Class-Incremental Learning — arXiv:2609.36759},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36759},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f1ef44be8fcb; sha256 fe2399cc52783b2b581594c550c915ce0aaab05052eaaa7ed475e522355b10b1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36759. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.36759 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T15:54:53.888Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).