Dual-Mode Low-Rank Learner with Bridge-Prototype Ensemble for Vision-Language Class-Incremental Learning
cs.CV, cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Comments: 21 pages, 11 figures, and 12 tables, including the appendix
Code: https://github.com/linlany/RAPF
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Continual Learning with Vision-Language Models via Semantic-Geometry Preservation
- Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning
- KeepLoRA: Continual Learning with Residual Gradient Adaptation
- Stabilizing the Modality Gap: Null-Space Projected Continual Learning for Vision-Language Models
- LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs
- CLIP model is an Efficient Continual Learner
- Adapter-Enhanced Semantic Prompting for Continual Learning
- Exploiting the Semantic Knowledge of Pre-trained Text-Encoders for Continual Learning
- Microsoft COCO Captions: Data Collection and Evaluation Server
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models