Original
发表于 2025-4-1 05:24:44
,SDPT: Synchronous Dual Prompt Tuning for Fusion-Based Visual-Language Pre-trained Models,ual-modal fusion-based visual-language pre-trained models (VLPMs), such as GLIP, has encountered issues. Existing prompt tuning methods have not effectively addressed the modal mapping and aligning problem for tokens in different modalities, leading to poor transfer generalization. To address this i
窃喜
发表于 2025-4-1 08:45:30
Lecture Notes in Computer Sciencehttp://image.papertrans.cn/d/image/242333.jpg
小溪
发表于 2025-4-1 11:02:55
http://reply.papertrans.cn/25/2424/242333/242333_63.png
2否定
发表于 2025-4-1 16:32:43
https://doi.org/10.1007/978-3-642-85555-9ing (FSCIL) faces several challenges, such as overfitting and catastrophic forgetting. Such a challenging problem is often tackled by fixing a feature extractor trained on base classes to reduce the adverse effects of overfitting and forgetting. Under such formulation, our primary focus is represent