Similarity-Aware Selective State-Space Modeling for Semantic Correspondence

• URL: http://arxiv.org/abs/2509.24318v1
• Date: Mon, 29 Sep 2025 05:56:57 GMT
• Title: Similarity-Aware Selective State-Space Modeling for Semantic Correspondence
• Authors: Seungwook Kim, Minsu Cho,
• Abstract summary: MambaMatcher efficiently models high-dimensional correlations using selective state-space models (SSMs)<n>MambaMatcher refines the 4D correlation map effectively without compromising feature map resolution or receptive field.<n> Experiments on standard semantic correspondence benchmarks demonstrate that MambaMatcher achieves state-of-the-art performance.
• Score: 54.92596581841942
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Establishing semantic correspondences between images is a fundamental yet challenging task in computer vision. Traditional feature-metric methods enhance visual features but may miss complex inter-correlation relationships, while recent correlation-metric approaches are hindered by high computational costs due to processing 4D correlation maps. We introduce MambaMatcher, a novel method that overcomes these limitations by efficiently modeling high-dimensional correlations using selective state-space models (SSMs). By implementing a similarity-aware selective scan mechanism adapted from Mamba's linear-complexity algorithm, MambaMatcher refines the 4D correlation map effectively without compromising feature map resolution or receptive field. Experiments on standard semantic correspondence benchmarks demonstrate that MambaMatcher achieves state-of-the-art performance.

Related papers

• BSMamba: Brightness and Semantic Modeling for Long-Range Interaction in Low-Light Image Enhancement [3.3392058493559693]
  Current low-light image enhancement (LLIE) methods face significant limitations in simultaneously improving brightness while preserving semantic consistency, fine details, and computational efficiency.<n>We propose BSMamba, a novel visual Mamba architecture comprising two specially designed components: Brightness Mamba and Semantic Mamba.<n>BSMamba achieves state-of-the-art performance in LLIE while preserving semantic consistency.
  arXiv  Detail & Related papers  (2025-06-23T07:04:34Z)
• Visual Explanation via Similar Feature Activation for Metric Learning [23.559106251249872]
  Class activation maps (CAM) have been extensively employed to explore the interpretability of softmax-based convolutional neural networks.<n>We propose a novel visual explanation method termed Similar Feature Activation Map (SFAM)<n>SFAM provides highly promising interpretable visual explanations for CNN models using Euclidean distance or cosine similarity as the similarity metric.
  arXiv  Detail & Related papers  (2025-06-02T13:14:37Z)
• Bridging the Modality Gap: Dimension Information Alignment and Sparse Spatial Constraint for Image-Text Matching [10.709744162565274]
  We propose a novel method called DIAS to bridge the modality gap from two aspects. The method achieves 4.3%-10.2% rSum improvements on Flickr30k and MSCOCO benchmarks.
  arXiv  Detail & Related papers  (2024-10-22T09:37:29Z)
• GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric Learning [51.677086019209554]
  We propose a Generalized Structural Sparse to capture powerful relationships across modalities for pair-wise similarity learning. The distance metric delicately encapsulates two formats of diagonal and block-diagonal terms. Experiments on cross-modal and two extra uni-modal retrieval tasks have validated its superiority and flexibility.
  arXiv  Detail & Related papers  (2024-10-20T03:45:50Z)
• Efficient Semantic Matching with Hypercolumn Correlation [58.92933923647451]
  HCCNet is an efficient yet effective semantic matching method. It exploits the full potential of multi-scale correlation maps. It eschews the reliance on expensive match-wise relationship mining on the 4D correlation map.
  arXiv  Detail & Related papers  (2023-11-07T20:40:07Z)
• FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network [48.912196729711624]
  Few-shot semantic segmentation is the task of learning to locate each pixel of a novel class in a query image with only a few annotated support images. We propose a Feature-Enhanced Context-Aware Network (FECANet) to suppress the matching noise caused by inter-class local similarity. In addition, we propose a novel correlation reconstruction module that encodes extra correspondence relations between foreground and background and multi-scale context semantic features.
  arXiv  Detail & Related papers  (2023-01-19T16:31:13Z)
• Deep Relational Metric Learning [84.95793654872399]
  This paper presents a deep relational metric learning framework for image clustering and retrieval. We learn an ensemble of features that characterizes an image from different aspects to model both interclass and intraclass distributions. Experiments on the widely-used CUB-200-2011, Cars196, and Stanford Online Products datasets demonstrate that our framework improves existing deep metric learning methods and achieves very competitive results.
  arXiv  Detail & Related papers  (2021-08-23T09:31:18Z)
• Semantic Correspondence with Transformers [68.37049687360705]
  We propose Cost Aggregation with Transformers (CATs) to find dense correspondences between semantically similar images. We include appearance affinity modelling to disambiguate the initial correlation maps and multi-level aggregation. We conduct experiments to demonstrate the effectiveness of the proposed model over the latest methods and provide extensive ablation studies.
  arXiv  Detail & Related papers  (2021-06-04T14:39:03Z)

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.