语义关系增强的CLIP适配器用于域自适应零样本学习
Semantic Relation-Enhanced CLIP Adapter for Domain Adaptive Zero-Shot Learning
AI总结：
针对域自适应零样本学习，提出语义关系增强的CLIP适配器框架，通过语义关系结构损失和跨模态对齐保留策略，在I2AwA和I2WebV基准上达到最先进性能。
摘要：
数据标注的高成本促使了在数据有限场景下训练深度学习模型的研究。然而，现有范式未能平衡跨域迁移和跨类别泛化，从而产生了对域自适应零样本学习（DAZSL）的需求。尽管视觉-语言模型（如CLIP）在DAZSL领域具有固有优势，但当前研究并未充分利用其潜力。将CLIP应用于DAZSL面临两个核心挑战：由于缺乏语义关系指导导致的跨类别知识迁移效率低下，以及在目标域微调过程中跨模态对齐性能下降。为解决这些问题，我们提出了语义关系增强的CLIP（SRE-CLIP）适配器框架，该框架整合了语义关系结构损失和跨模态对齐保留策略。作为首个基于CLIP的DAZSL方法，SRE-CLIP在I2AwA和I2WebV基准上取得了最先进的性能，显著优于现有方法。
英文摘要：
The high cost of data annotation has spurred research on training deep learning models in data-limited scenarios. Existing paradigms, however, fail to balance cross-domain transfer and cross-category generalization, giving rise to the demand for Domain-Adaptive Zero-Shot Learning (DAZSL). Although vision-language models (e.g., CLIP) have inherent advantages in the DAZSL field, current studies do not fully exploit their potential. Applying CLIP to DAZSL faces two core challenges: inefficient cross-category knowledge transfer due to the lack of semantic relation guidance, and degraded cross-modal alignment during target domain fine-tuning. To address these issues, we propose a Semantic Relation-Enhanced CLIP (SRE-CLIP) Adapter framework, integrating a Semantic Relation Structure Loss and a Cross-Modal Alignment Retention Strategy. As the first CLIP-based DAZSL method, SRE-CLIP achieves state-of-the-art performance on the I2AwA and I2WebV benchmarks, significantly outperforming existing approaches.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
