多模态结构学习：通过跨模态图拉索解耦共享和特定拓扑
Multimodal Structure Learning: Disentangling Shared and Specific Topology via Cross-Modal Graphical Lasso
AI总结：
本文提出跨模态图拉索方法，通过统一视觉语言编码器和跨注意力蒸馏机制，解耦共享与类别特定拓扑，提升多模态表征的可解释性。
摘要：
学习可解释的多模态表示本质上依赖于揭示异质特征间的条件依赖关系。然而，图拉索等稀疏图估计技术在视觉-语言领域受到高维噪声、模态对齐和共享与类别特定拓扑混淆的严重限制。本文提出跨模态图拉索（CM-GLasso），通过结合新的文本-可视化策略和统一视觉语言编码器，严格对齐多模态特征到共享潜在空间。我们引入跨注意力蒸馏机制，将高维片段压缩为显式语义节点，自然提取空间感知的跨模态先验。此外，我们统一定制化的图拉索估计和共享-特定结构学习（CSSL）为一个联合目标，通过交替方向乘数法（ADMM）优化。该方法保证同时解耦不变和类别特定的精度矩阵，无需多步误差累积。在八个涵盖自然和医学领域的基准测试中，CM-GLasso在生成分类和密集语义分割任务中建立了新的最先进的性能。
英文摘要：
Learning interpretable multimodal representations inherently relies on uncovering the conditional dependencies between heterogeneous features. However, sparse graph estimation techniques, such as Graphical Lasso (GLasso), to visual-linguistic domains is severely bottlenecked by high-dimensional noise, modality misalignment, and the confounding of shared versus category-specific topologies. In this paper, we propose Cross-Modal Graphical Lasso (CM-GLasso) that overcomes these fundamental limitations. By coupling a novel text-visualization strategy with a unified vision-language encoder, we strictly align multimodal features into a shared latent space. We introduce a cross-attention distillation mechanism that condenses high-dimensional patches into explicit semantic nodes, naturally extracting spatial-aware cross-modal priors. Furthermore, we unify tailored GLasso estimation and Common-Specific Structure Learning (CSSL) into a joint objective optimized via the Alternating Direction Method of Multiplier (ADMM). This formulation guarantees the simultaneous disentanglement of invariant and class-specific precision matrices without multi-step error accumulation. Extensive experiments across eight benchmarks covering both natural and medical domains demonstrate that CM-GLasso establishes a new state-of-the-art in generative classification and dense semantic segmentation 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。
