Mamba Learns in Context: Structure-Aware Domain Generalization for Multi-Task Point Cloud Understanding

• URL: http://arxiv.org/abs/2603.20739v1
• Date: Sat, 21 Mar 2026 09:55:10 GMT
• Title: Mamba Learns in Context: Structure-Aware Domain Generalization for Multi-Task Point Cloud Understanding
• Abstract summary: We propose Structure-Aware Domain Generalization (SADG), a Mamba-based In-Context Learning framework that preserves structural hierarchy across domains and tasks.<n>SADG uses centroid-based topology and geodesic curvature continuity to generate transformation-invariant sequences.<n>It consistently outperforms state-of-the-art methods across multiple tasks including reconstruction, denoising, and registration.
• Score: 36.012422604739236
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While recent Transformer and Mamba architectures have advanced point cloud representation learning, they are typically developed for single-task or single-domain settings. Directly applying them to multi-task domain generalization (DG) leads to degraded performance. Transformers effectively model global dependencies but suffer from quadratic attention cost and lack explicit structural ordering, whereas Mamba offers linear-time recurrence yet often depends on coordinate-driven serialization, which is sensitive to viewpoint changes and missing regions, causing structural drift and unstable sequential modeling. In this paper, we propose Structure-Aware Domain Generalization (SADG), a Mamba-based In-Context Learning framework that preserves structural hierarchy across domains and tasks. We design structure-aware serialization (SAS) that generates transformation-invariant sequences using centroid-based topology and geodesic curvature continuity. We further devise hierarchical domain-aware modeling (HDM) that stabilizes cross-domain reasoning by consolidating intra-domain structure and fusing inter-domain relations. At test time, we introduce a lightweight spectral graph alignment (SGA) that shifts target features toward source prototypes in the spectral domain without updating model parameters, ensuring structure-preserving test-time feature shifting. In addition, we introduce MP3DObject, a real-scan object dataset for multi-task DG evaluation. Comprehensive experiments demonstrate that the proposed approach improves structural fidelity and consistently outperforms state-of-the-art methods across multiple tasks including reconstruction, denoising, and registration.

Related papers

• Continual Video-MLLM Adaptation over Evolving Domains [42.6837206153246]
  Video multimodal large language models have shown strong capability in video understanding, yet their adaptation to sequentially evolving domains remains underexplored.<n>We propose Distribution-Aware Expert Routing, a parameter-efficient framework for continual Video-MLLM adaptation over evolving domains.<n> Experiments on two strong Video-MLLM backbones show that DAER consistently outperforms prior methods.
  arXiv  Detail & Related papers  (2026-07-21T05:16:36Z)
• BiCLIP: Domain Canonicalization via Structured Geometric Transformation [4.679031868857942]
  BiCLIP is a framework that applies a targeted transformation to multimodal features to enhance cross-modal alignment.<n>Our approach is characterized by its extreme simplicity and low parameter footprint.
  arXiv  Detail & Related papers  (2026-03-09T21:26:15Z)
• MEMTS: Internalizing Domain Knowledge via Parameterized Memory for Retrieval-Free Domain Adaptation of Time Series Foundation Models [51.506429027626005]
  Memory for Time Series (MEMTS) is a lightweight and plug-and-play method for retrieval-free domain adaptation in time series forecasting.<n>Key component of MEMTS is a Knowledge Persistence Module (KPM), which internalizes domain-specific temporal dynamics.<n>This paradigm shift enables MEMTS to achieve accurate domain adaptation with constant-time inference and near-zero latency.
  arXiv  Detail & Related papers  (2026-02-14T14:00:06Z)
• SA^2GFM: Enhancing Robust Graph Foundation Models with Structure-Aware Semantic Augmentation [20.028450229306554]
  We present SA2GFM, a robust Graph Foundation Models (GFMs) framework that improves domain-adaptive representations.<n>We show that SA2GFM outperforms 9 state-of-the-art baselines in terms of effectiveness and robustness against random noise and adversarial perturbations for node and graph classification.
  arXiv  Detail & Related papers  (2025-11-26T08:26:01Z)
• FOUND: Fourier-based von Mises Distribution for Robust Single Domain Generalization in Object Detection [46.14695068852788]
  Single Domain Generalization for object detection aims to train a model on a single source domain that can generalize effectively to unseen target domains.<n>We propose a novel framework that enhances object detection by integrating the von Mises-Fisher (vMF) distribution and Fourier transformation into a CLIP-guided pipeline.<n>Our method not only preserves the semantic alignment benefits of CLIP but also enriches feature diversity and structural consistency across domains.
  arXiv  Detail & Related papers  (2025-11-13T14:28:10Z)
• Time Series Domain Adaptation via Latent Invariant Causal Mechanism [28.329164754662354]
  Time series domain adaptation aims to transfer the complex temporal dependence from the labeled source domain to the unlabeled target domain.<n>Recent advances leverage the stable causal mechanism over observed variables to model the domain-invariant temporal dependence.<n>However, modeling precise causal structures in high-dimensional data, such as videos, remains challenging.
  arXiv  Detail & Related papers  (2025-02-23T16:25:58Z)
• START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation [27.301312891532277]
  Domain Generalization (DG) aims to enable models to generalize to unseen target domains by learning from multiple source domains.<n>We propose START, which achieves state-of-the-art (SOTA) performances and offers a competitive alternative to CNNs and ViTs.<n>Our START can selectively perturb and suppress domain-specific features in salient tokens within the input-dependent matrices of SSMs, thus effectively reducing the discrepancy between different domains.
  arXiv  Detail & Related papers  (2024-10-21T13:50:32Z)
• PointDGMamba: Domain Generalization of Point Cloud Classification via Generalized State Space Model [77.00221501105788]
  Domain Generalization (DG) has been recently explored to improve the generalizability of point cloud classification.<n>We present the first work that studies the generalizability of state space models (SSMs) in DG PCC.<n>We propose a novel framework, PointDGMamba, that excels in strong generalizability toward unseen domains.
  arXiv  Detail & Related papers  (2024-08-24T12:53:48Z)
• StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization [85.18995948334592]
  Single domain generalization (single DG) aims at learning a robust model generalizable to unseen domains from only one training domain. State-of-the-art approaches have mostly relied on data augmentations, such as adversarial perturbation and style enhancement, to synthesize new data. We propose emphStyDeSty, which explicitly accounts for the alignment of the source and pseudo domains in the process of data augmentation.
  arXiv  Detail & Related papers  (2024-06-01T02:41:34Z)
• HCVP: Leveraging Hierarchical Contrastive Visual Prompt for Domain Generalization [69.33162366130887]
  Domain Generalization (DG) endeavors to create machine learning models that excel in unseen scenarios by learning invariant features. We introduce a novel method designed to supplement the model with domain-level and task-specific characteristics. This approach aims to guide the model in more effectively separating invariant features from specific characteristics, thereby boosting the generalization.
  arXiv  Detail & Related papers  (2024-01-18T04:23:21Z)
• DepGraph: Towards Any Structural Pruning [68.40343338847664]
  We study general structural pruning of arbitrary architecture like CNNs, RNNs, GNNs and Transformers. We propose a general and fully automatic method, emphDependency Graph (DepGraph), to explicitly model the dependency between layers and comprehensively group parameters for pruning. In this work, we extensively evaluate our method on several architectures and tasks, including ResNe(X)t, DenseNet, MobileNet and Vision transformer for images, GAT for graph, DGCNN for 3D point cloud, alongside LSTM for language, and demonstrate that, even with a
  arXiv  Detail & Related papers  (2023-01-30T14:02:33Z)
• AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection [90.18752912204778]
  Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications. We propose a novel augmented feature alignment network (AFAN) which integrates intermediate domain image generation and domain-adversarial training. Our approach significantly outperforms the state-of-the-art methods on standard benchmarks for both similar and dissimilar domain adaptations.
  arXiv  Detail & Related papers  (2021-06-10T05:01:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.