CrossFlowDG：通过跨模态流匹配弥合模态差距以实现领域泛化
CrossFlowDG: Bridging the Modality Gap with Cross-modal Flow Matching for Domain Generalization
AI总结：
本文提出CrossFlowDG，通过无噪声的跨模态流匹配解决领域泛化中的模态差距问题，利用联合欧几里得潜在空间中的连续变换，将领域偏向的图像嵌入向领域不变的文本嵌入迁移。
摘要：
领域泛化（DG）旨在保持领域偏移下的性能，这在计算机视觉中主要表现为风格变化导致模型过度拟合领域特定的外观线索而非类别语义。为克服此问题，近期方法使用文本表示作为稳定的、领域不变的锚点。然而，依赖余弦相似度的对比对齐的多模态方法仍存在模态差距，导致图像和文本嵌入在几何上分离，尽管存在语义对应。本文提出CrossFlowDG，一种新的DG框架，通过无噪声的跨模态流匹配解决此残余差距。通过高效的VMamba图像编码器和CLIP的文本编码器，CrossFlowDG在四个常见DG基准测试中进行测试，其在多个基准上表现竞争，而在TerraIncognita上达到最先进的性能。代码可在：https://github.com/ajkrit/CrossFlowDG获取。
英文摘要：
Domain generalization (DG) aims to maintain performance under domain shift, which in computer vision appears primarily as stylistic variations that cause models to overfit to domain-specific appearance cues rather than class semantics. To overcome this, recent methods use textual representations as stable, domain-invariant anchors. However, multimodal approaches that rely on cosine similarity-based contrastive alignment leave a modality gap where image and text embeddings remain geometrically separated despite semantic correspondence. We propose CrossFlowDG, a novel DG framework that addresses this residual gap using noise-free, cross-modal flow matching. By learning a continuous transformation in the joint Euclidean latent space, our framework explicitly transports domain-biased image embeddings toward domain-invariant text embeddings of the correct class. Using the efficient VMamba image encoder and CLIP's text encoder, CrossFlowDG is tested against four common DG benchmarks, and achieves competitive performance on several benchmarks and state-of-the-art on TerraIncognita. Code is available at: https://github.com/ajkrit/CrossFlowDG
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。
