弥合语义鸿沟：协同概念锚定用于通用少样本和零样本OOD感知
Bridging the Semantic Chasm: Synergistic Conceptual Anchoring for Generalized Few-Shot and Zero-Shot OOD Perception
AI总结：
SynerNet通过协同神经代理网络框架，解决视觉语言模型在分布外概念感知中的跨模态对齐退化问题，提升少样本和零样本场景下的精度。
摘要：
本文提出了一种开创性的协同神经代理网络（SynerNet）框架，旨在缓解在遇到分布外（OOD）概念时视觉语言模型（VLMs）中跨模态对齐退化现象。具体而言，四个专门的计算单元——视觉感知、语言上下文、名词嵌入和全局协调——通过结构化的消息传播协议协同纠正模态差异。主要贡献包括一个多代理潜在空间命名获取框架、一种增强少样本适应的语义上下文交换算法，以及一种自适应动态平衡机制。在VISTA-Beyond基准上的实验证明，SynerNet在少样本和零样本场景中均实现了显著的性能提升，在各种各样的领域中，精度提高了1.2%至5.4%。
英文摘要：
This manuscript presents a pioneering Synergistic Neural Agents Network (SynerNet) framework designed to mitigate the phenomenon of cross-modal alignment degeneration in Vision-Language Models (VLMs) when encountering Out-of-Distribution (OOD) concepts. Specifically, four specialized computational units - visual perception, linguistic context, nominal embedding, and global coordination - collaboratively rectify modality disparities via a structured message-propagation protocol. The principal contributions encompass a multi-agent latent space nomenclature acquisition framework, a semantic context-interchange algorithm for enhanced few-shot adaptation, and an adaptive dynamic equilibrium mechanism. Empirical evaluations conducted on the VISTA-Beyond benchmark demonstrate that SynerNet yields substantial performance augmentations in both few-shot and zero-shot scenarios, exhibiting precision improvements ranging from 1.2% to 5.4% across a diverse array of domains.
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。
