arXiv 2512.088202025-12-09cs.CVcs.AI

无需训练的双双曲适配器用于更高效的跨模态推理

Training-Free Dual Hyperbolic Adapters for Better Cross-Modal Reasoning

College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机科学与软件工程学院）；Department of Electrical and Electronic Engineering, Southern University of Science and Technology（南方科技大学电子与电气工程系）；Department of Applied Mathematics and Theoretical Physics, University of Cambridge（剑桥大学应用数学与理论物理系）；Yau Mathematical Sciences Center, Tsinghua University（清华大学应用数学中心）

Yi Zhang, Chun-Wun Cheng, Junyi He, Ke Yu, Yushun Tang, Carola-Bibiane Schönlieb, Zhihai He, Angelica I. Aviles-Rivero

备注：: Accepted in IEEE Transactions on Multimedia (TMM)

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出无需训练的双双曲适配器方法，通过双曲空间嵌入提升跨模态推理性能，实现更高效的领域泛化和少样本识别。

摘要：

最近关于视觉-语言模型（VLMs）的研究显著提高了我们在跨模态推理方面的能力。然而，现有方法在领域变化时会出现性能下降，或需要大量计算资源进行新领域的微调。为了解决这个问题，我们开发了一种新的大视觉-语言模型适应方法，称为

英文摘要：

Recent research in Vision-Language Models (VLMs) has significantly advanced our capabilities in cross-modal reasoning. However, existing methods suffer from performance degradation with domain changes or require substantial computational resources for fine-tuning in new domains. To address this issue, we develop a new adaptation method for large vision-language models, called \textit{Training-free Dual Hyperbolic Adapters} (T-DHA). We characterize the vision-language relationship between semantic concepts, which typically has a hierarchical tree structure, in the hyperbolic space instead of the traditional Euclidean space. Hyperbolic spaces exhibit exponential volume growth with radius, unlike the polynomial growth in Euclidean space. We find that this unique property is particularly effective for embedding hierarchical data structures using the Poincaré ball model, achieving significantly improved representation and discrimination power. Coupled with negative learning, it provides more accurate and robust classifications with fewer feature dimensions. Our extensive experimental results on various datasets demonstrate that the T-DHA method significantly outperforms existing state-of-the-art methods in few-shot image recognition and domain generalization tasks.

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。