AI RESEARCH
DesCLIP: Robust Continual Learning via General Attribute Descriptions for VLM-Based Visual Recognition
arXiv CS.AI
•
ArXi:2502.00618v3 Announce Type: replace-cross Continual learning of vision-language models (VLMs) focuses on leveraging cross-modal pretrained knowledge to incrementally adapt to expanding downstream tasks and datasets, while tackling the challenge of knowledge forgetting. Existing research often focuses on connecting visual features with specific class text in downstream tasks, overlooking the latent relationships between general and specialized knowledge.