Domain Generalization through Spatial Relation Induction over Visual Primitives

• URL: http://arxiv.org/abs/2605.06043v1
• Date: Thu, 07 May 2026 11:31:46 GMT
• Title: Domain Generalization through Spatial Relation Induction over Visual Primitives
• Abstract summary: Primitive-Aware Structure for domain gEneralization (PARSE) is an image classification framework that factors visual recognition visual primitives and their relational composition.<n>We represent these compositions using soft binary, ternary, and quaternary predicates over primitive locations, yielding differentiable measures of spatial alignment that can be learned end-to-end.<n>Across CUB-DG and the DomainBed benchmark suite,PARSE improves accuracy by over 4.5 percentage points on CUB-DG and remains competitive with existing DG methods on DomainBed.
• Score: 4.085285915236828
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Domain generalization requires identifying stable representations that support reliable classification across domains. Most existing methods seek such stability through improving the training process, for example, through model selection strategies, data augmentation, or feature-alignment objectives. Although these strategies can be effective, they leave the representation learning of structural composition implicit, which may limit performance on compositional domain generalization benchmarks. In this work, we propose Primitive-Aware Relational Structure for domain gEneralization (PARSE), an image classification framework that factors visual recognition into visual primitives and their relational composition. We represent these compositions using soft binary, ternary, and quaternary predicates over primitive locations, yielding differentiable measures of spatial alignment that can be learned end-to-end. To learn primitives and relational structures jointly, we design an end-to-end architecture with three components: (1) a convolutional neural network (CNN) backbone that extracts general visual features, (2) a concept bottleneck layer that maps these features to primitive heatmaps with differentiable spatial coordinates, and (3) a structural scoring layer that evaluates candidate spatial relations among the detected primitives. We then compute class probability from the joint evidence of its class-specific relational compositions. Across CUB-DG and the DomainBed benchmark suite,PARSE improves accuracy by over 4.5 percentage points on CUB-DG and remains competitive with existing DG methods on DomainBed.

Related papers

• Unsupervised Domain Adaptation for Sim-to-Real Object Pose Estimation with Contrastive Alignment and Pseudo-Label Refinement [14.854437007037683]
  Unsupervised domain adaptation (UDA) enables robust transfer of knowledge from simulated to real environments.<n>We introduce CAPLR that targets the adaptation of pose-sensitive features in localized regions.<n>We show that CAPLR achieves state-of-the-art performance across multiple well-known object pose estimation benchmarks.
  arXiv  Detail & Related papers  (2026-06-19T10:11:17Z)
• Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers [93.3976834364707]
  We propose sREPA, a structural REPresentation Alignment framework to enforce consistency in the relational geometry of feature maps.<n>By encouraging the model to internalize holistic spatial layouts and structural correlations from pre-trained features, sREPA achieves faster and more stable convergence.
  arXiv  Detail & Related papers  (2026-05-16T12:01:04Z)
• GenCape: Structure-Inductive Generative Modeling for Category-Agnostic Pose Estimation [22.606848016741107]
  Category-agnostic pose estimation (CAPE) aims to localize keypoints on query images from arbitrary categories.<n>We propose GenCape, a Generative-based framework for CAPE that infers keypoint relationships solely from image-based support inputs.
  arXiv  Detail & Related papers  (2026-05-13T08:17:20Z)
• Towards Multiscale Graph-based Protein Learning with Geometric Secondary Structural Motifs [10.433254687685038]
  Graph neural networks (GNNs) have emerged as powerful tools for learning protein structures.<n>We propose an efficient multiscale graph-based learning framework tailored to proteins.
  arXiv  Detail & Related papers  (2026-01-31T18:50:24Z)
• Hierarchical Neural Semantic Representation for 3D Semantic Correspondence [72.8101601086805]
  We design the hierarchical neural semantic representation (HNSR), which consists of a global semantic feature to capture high-level structure and multi-resolution local geometric features.<n>Second, we design a progressive global-to-local matching strategy, which establishes coarse semantic correspondence using the global semantic feature.<n>Third, our framework is training-free and broadly compatible with various pre-trained 3D generative backbones, demonstrating strong generalization across diverse shape categories.
  arXiv  Detail & Related papers  (2025-09-22T07:23:07Z)
• Adaptive Betweenness Clustering for Semi-Supervised Domain Adaptation [108.40945109477886]
  We propose a novel SSDA approach named Graph-based Adaptive Betweenness Clustering (G-ABC) for achieving categorical domain alignment. Our method outperforms previous state-of-the-art SSDA approaches, demonstrating the superiority of the proposed G-ABC algorithm.
  arXiv  Detail & Related papers  (2024-01-21T09:57:56Z)
• Unsupervised Domain Adaptation for Point Cloud Semantic Segmentation via Graph Matching [14.876681993079062]
  We propose a graph-based framework to explore the local-level feature alignment between the two domains. We also formulate a category-guided contrastive loss to guide the segmentation model to learn discriminative features on the target domain.
  arXiv  Detail & Related papers  (2022-08-09T02:30:15Z)
• SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation [94.11915008006483]
  We propose SemAffiNet for point cloud semantic segmentation. We conduct extensive experiments on the ScanNetV2 and NYUv2 datasets.
  arXiv  Detail & Related papers  (2022-05-26T17:00:23Z)
• Domain Generalisation for Object Detection under Covariate and Concept Shift [10.32461766065764]
  Domain generalisation aims to promote the learning of domain-invariant features while suppressing domain-specific features. An approach to domain generalisation for object detection is proposed, the first such approach applicable to any object detection architecture.
  arXiv  Detail & Related papers  (2022-03-10T11:14:18Z)
• Unveiling the Potential of Structure-Preserving for Weakly Supervised Object Localization [71.79436685992128]
  We propose a two-stage approach, termed structure-preserving activation (SPA), towards fully leveraging the structure information incorporated in convolutional features for WSOL. In the first stage, a restricted activation module (RAM) is designed to alleviate the structure-missing issue caused by the classification network. In the second stage, we propose a post-process approach, termed self-correlation map generating (SCG) module to obtain structure-preserving localization maps.
  arXiv  Detail & Related papers  (2021-03-08T03:04:14Z)
• Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering [119.88565565454378]
  Unsupervised domain adaptation (UDA) is to learn classification models that make predictions for unlabeled data on a target domain. We propose a hybrid model of Structurally Regularized Deep Clustering, which integrates the regularized discriminative clustering of target data with a generative one. Our proposed H-SRDC outperforms all the existing methods under both the inductive and transductive settings.
  arXiv  Detail & Related papers  (2020-12-08T08:52:00Z)
• Bi-Directional Generation for Unsupervised Domain Adaptation [61.73001005378002]
  Unsupervised domain adaptation facilitates the unlabeled target domain relying on well-established source domain information. Conventional methods forcefully reducing the domain discrepancy in the latent space will result in the destruction of intrinsic data structure. We propose a Bi-Directional Generation domain adaptation model with consistent classifiers interpolating two intermediate domains to bridge source and target domains.
  arXiv  Detail & Related papers  (2020-02-12T09:45:39Z)

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.