CorrMoE: Mixture of Experts with De-stylization Learning for Cross-Scene and Cross-Domain Correspondence Pruning

• URL: http://arxiv.org/abs/2507.11834v1
• Date: Wed, 16 Jul 2025 01:44:01 GMT
• Title: CorrMoE: Mixture of Experts with De-stylization Learning for Cross-Scene and Cross-Domain Correspondence Pruning
• Authors: Peiwen Xia, Tangfei Liao, Wei Zhu, Danhuai Zhao, Jianjun Ke, Kaihao Zhang, Tong Lu, Tao Wang,
• Abstract summary: CorrMoE is a correspondence pruning framework that enhances robustness under cross-domain and cross-scene variations.<n>For scene diversity, we design a Bi-Fusion Mixture of Experts module that adaptively integrates multi-perspective features.<n>Experiments on benchmark datasets demonstrate that CorrMoE achieves superior accuracy and generalization compared to state-of-the-art methods.
• Score: 30.111296778234124
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Establishing reliable correspondences between image pairs is a fundamental task in computer vision, underpinning applications such as 3D reconstruction and visual localization. Although recent methods have made progress in pruning outliers from dense correspondence sets, they often hypothesize consistent visual domains and overlook the challenges posed by diverse scene structures. In this paper, we propose CorrMoE, a novel correspondence pruning framework that enhances robustness under cross-domain and cross-scene variations. To address domain shift, we introduce a De-stylization Dual Branch, performing style mixing on both implicit and explicit graph features to mitigate the adverse influence of domain-specific representations. For scene diversity, we design a Bi-Fusion Mixture of Experts module that adaptively integrates multi-perspective features through linear-complexity attention and dynamic expert routing. Extensive experiments on benchmark datasets demonstrate that CorrMoE achieves superior accuracy and generalization compared to state-of-the-art methods. The code and pre-trained models are available at https://github.com/peiwenxia/CorrMoE.

Related papers

• Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations [5.971046215117033]
  Imitation learning (IL) enables agents to mimic expert behavior without reward signals but faces challenges in cross-domain scenarios with high-dimensional, noisy, and incomplete visual observations.<n>We propose Domain-Invariant Per-Frame Feature Extraction for Imitation Learning (DIFF-IL), a novel IL method that extracts domain-invariant features from individual frames and adapts them into sequences to isolate and replicate expert behaviors.
  arXiv  Detail & Related papers  (2025-02-05T03:52:36Z)
• Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints [15.541287957548771]
  We propose a Coarse-to-fine Consistency Constraints Visual Grounding architecture.<n>It integrates implicit and explicit modeling approaches within a two-stage framework.<n>It significantly outperforms state-of-the-art REC and RIS methods by a substantial margin.
  arXiv  Detail & Related papers  (2025-01-12T04:30:13Z)
• Robust Scene Change Detection Using Visual Foundation Models and Cross-Attention Mechanisms [27.882122236282054]
  We present a novel method for scene change detection that leverages the robust feature extraction capabilities of a visual foundational model, DINOv2.<n>We evaluate our approach on two benchmark datasets, VL-CMU-CD and PSCD, along with their viewpoint-varied versions.<n>Our experiments demonstrate significant improvements in F1-score, particularly in scenarios involving geometric changes between image pairs.
  arXiv  Detail & Related papers  (2024-09-25T11:55:27Z)
• Cross-Domain Separable Translation Network for Multimodal Image Change Detection [11.25422609271201]
  multimodal change detection (MCD) is particularly critical in the remote sensing community. This paper focuses on addressing the challenges of MCD, especially the difficulty in comparing images from different sensors. A novel unsupervised cross-domain separable translation network (CSTN) is proposed to overcome these limitations.
  arXiv  Detail & Related papers  (2024-07-23T03:56:02Z)
• Unified Frequency-Assisted Transformer Framework for Detecting and Grounding Multi-Modal Manipulation [109.1912721224697]
  We present the Unified Frequency-Assisted transFormer framework, named UFAFormer, to address the DGM4 problem. By leveraging the discrete wavelet transform, we decompose images into several frequency sub-bands, capturing rich face forgery artifacts. Our proposed frequency encoder, incorporating intra-band and inter-band self-attentions, explicitly aggregates forgery features within and across diverse sub-bands.
  arXiv  Detail & Related papers  (2023-09-18T11:06:42Z)
• Improving Anomaly Segmentation with Multi-Granularity Cross-Domain Alignment [17.086123737443714]
  Anomaly segmentation plays a pivotal role in identifying atypical objects in images, crucial for hazard detection in autonomous driving systems. While existing methods demonstrate noteworthy results on synthetic data, they often fail to consider the disparity between synthetic and real-world data domains. We introduce the Multi-Granularity Cross-Domain Alignment framework, tailored to harmonize features across domains at both the scene and individual sample levels.
  arXiv  Detail & Related papers  (2023-08-16T22:54:49Z)
• Bilevel Fast Scene Adaptation for Low-Light Image Enhancement [50.639332885989255]
  Enhancing images in low-light scenes is a challenging but widely concerned task in the computer vision. Main obstacle lies in the modeling conundrum from distribution discrepancy across different scenes. We introduce the bilevel paradigm to model the above latent correspondence. A bilevel learning framework is constructed to endow the scene-irrelevant generality of the encoder towards diverse scenes.
  arXiv  Detail & Related papers  (2023-06-02T08:16:21Z)
• Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization [113.03189252044773]
  We propose a unified framework, Style-HAllucinated Dual consistEncy learning (SHADE), to handle domain shift in various visual tasks. Our versatile SHADE can significantly enhance the generalization in various visual recognition tasks, including image classification, semantic segmentation and object detection.
  arXiv  Detail & Related papers  (2022-12-18T11:42:51Z)
• Marginal Contrastive Correspondence for Guided Image Generation [58.0605433671196]
  Exemplar-based image translation establishes dense correspondences between a conditional input and an exemplar from two different domains. Existing work builds the cross-domain correspondences implicitly by minimizing feature-wise distances across the two domains. We design a Marginal Contrastive Learning Network (MCL-Net) that explores contrastive learning to learn domain-invariant features for realistic exemplar-based image translation.
  arXiv  Detail & Related papers  (2022-04-01T13:55:44Z)
• Adversarial Bipartite Graph Learning for Video Domain Adaptation [50.68420708387015]
  Domain adaptation techniques, which focus on adapting models between distributionally different domains, are rarely explored in the video recognition area. Recent works on visual domain adaptation which leverage adversarial learning to unify the source and target video representations are not highly effective on the videos. This paper proposes an Adversarial Bipartite Graph (ABG) learning framework which directly models the source-target interactions.
  arXiv  Detail & Related papers  (2020-07-31T03:48:41Z)
• Co-Attention for Conditioned Image Matching [91.43244337264454]
  We propose a new approach to determine correspondences between image pairs in the wild under large changes in illumination, viewpoint, context, and material. While other approaches find correspondences between pairs of images by treating the images independently, we instead condition on both images to implicitly take account of the differences between them.
  arXiv  Detail & Related papers  (2020-07-16T17:32:00Z)

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.