# Multimodal Structure Learning: Disentangling Shared and Specific Topology via Cross-Modal Graphical Lasso

arXiv: https://arxiv.org/abs/2604.03953 · HTML: https://mlsanity.com/paper/2604.03953/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 49 references that are in the map.
- First posted on arXiv 5 Apr 2026.

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Kvasir-SEG: A Segmented Polyp Dataset](https://mlsanity.com/paper/1911.07069/) (2019)
- [GroupViT: Semantic Segmentation Emerges from Text Supervision](https://mlsanity.com/paper/2202.11094/) (2022)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [OneFormer: One Transformer to Rule Universal Image Segmentation](https://mlsanity.com/paper/2211.06220/) (2022)
- [Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning](https://mlsanity.com/paper/2210.08823/) (2022)
- [PaliGemma 2: A Family of Versatile VLMs for Transfer](https://mlsanity.com/paper/2412.03555/) (2024)
- [Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers](https://mlsanity.com/paper/2108.06932/) (2021)
- [NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reduction](https://mlsanity.com/paper/1801.08297/) (2018)
- [CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2212.09506/) (2022)
- [Online Prototype Learning for Online Continual Learning](https://mlsanity.com/paper/2308.00301/) (2023)
- [Learning with Mixture of Prototypes for Out-of-Distribution Detection](https://mlsanity.com/paper/2402.02653/) (2024)
- [Visual Fourier Prompt Tuning](https://mlsanity.com/paper/2411.01327/) (2024)
- [Tangent Model Composition for Ensembling and Continual Fine-tuning](https://mlsanity.com/paper/2307.08114/) (2023)
- [DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers](https://mlsanity.com/paper/2505.23694/) (2025)
- [OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning](https://mlsanity.com/paper/2507.13364/) (2025)
- [PRO-VPT: Distribution-Adaptive Visual Prompt Tuning via Prompt Relocation](https://mlsanity.com/paper/2503.06901/) (2025)
- [Astroformer: More Data Might not be all you need for Classification](https://mlsanity.com/paper/2304.05350/) (2023)
- [Auxiliary Tasks Enhanced Dual-affinity Learning for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2403.01156/) (2024)
- [Confusing Pair Correction Based on Category Prototype for Domain Adaptation under Noisy Environments](https://mlsanity.com/paper/2403.12883/) (2024)

## Abstract (arXiv)

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.