A Sparse Graph Formulation for Efficient Spectral Image Segmentation

• URL: http://arxiv.org/abs/2306.13166v3
• Date: Fri, 7 Jun 2024 17:37:16 GMT
• Title: A Sparse Graph Formulation for Efficient Spectral Image Segmentation
• Authors: Rahul Palnitkar, Jeova Farias Sales Rocha Neto,
• Abstract summary: Spectral Clustering is one of the most traditional methods to solve segmentation problems. We adopt a sparse graph formulation based on the inclusion of extra nodes to a simple grid graph. Applying the original Normalized Cuts algorithm to this graph leads to a simple and scalable method for spectral image segmentation.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Spectral Clustering is one of the most traditional methods to solve segmentation problems. Based on Normalized Cuts, it aims at partitioning an image using an objective function defined by a graph. Despite their mathematical attractiveness, spectral approaches are traditionally neglected by the scientific community due to their practical issues and underperformance. In this paper, we adopt a sparse graph formulation based on the inclusion of extra nodes to a simple grid graph. While the grid encodes the pixel spatial disposition, the extra nodes account for the pixel color data. Applying the original Normalized Cuts algorithm to this graph leads to a simple and scalable method for spectral image segmentation, with an interpretable solution. Our experiments also demonstrate that our proposed methodology over performs both traditional and modern unsupervised algorithms for segmentation in both real and synthetic data.

Related papers

• Spectral Greedy Coresets for Graph Neural Networks [61.24300262316091]
  The ubiquity of large-scale graphs in node-classification tasks hinders the real-world applications of Graph Neural Networks (GNNs) This paper studies graph coresets for GNNs and avoids the interdependence issue by selecting ego-graphs based on their spectral embeddings. Our spectral greedy graph coreset (SGGC) scales to graphs with millions of nodes, obviates the need for model pre-training, and applies to low-homophily graphs.
  arXiv  Detail & Related papers  (2024-05-27T17:52:12Z)
• Patch-Based Deep Unsupervised Image Segmentation using Graph Cuts [0.0]
  We propose a patch-based unsupervised image segmentation strategy that bridges advances in unsupervised feature extraction with the algorithmic help of classical graph-based methods. We show that a simple convolutional neural network, trained to classify image patches, naturally leads to a state-of-the-art fully-convolutional unsupervised pixel-level segmenter.
  arXiv  Detail & Related papers  (2023-11-01T19:59:25Z)
• Spectral-Spatial Global Graph Reasoning for Hyperspectral Image Classification [50.899576891296235]
  Convolutional neural networks have been widely applied to hyperspectral image classification. Recent methods attempt to address this issue by performing graph convolutions on spatial topologies.
  arXiv  Detail & Related papers  (2021-06-26T06:24:51Z)
• Multilayer Graph Clustering with Optimized Node Embedding [70.1053472751897]
  multilayer graph clustering aims at dividing the graph nodes into categories or communities. We propose a clustering-friendly embedding of the layers of a given multilayer graph. Experiments show that our method leads to a significant improvement.
  arXiv  Detail & Related papers  (2021-03-30T17:36:40Z)
• Unrolling of Deep Graph Total Variation for Image Denoising [106.93258903150702]
  In this paper, we combine classical graph signal filtering with deep feature learning into a competitive hybrid design. We employ interpretable analytical low-pass graph filters and employ 80% fewer network parameters than state-of-the-art DL denoising scheme DnCNN.
  arXiv  Detail & Related papers  (2020-10-21T20:04:22Z)
• Line Graph Neural Networks for Link Prediction [71.00689542259052]
  We consider the graph link prediction task, which is a classic graph analytical problem with many real-world applications. In this formalism, a link prediction problem is converted to a graph classification task. We propose to seek a radically different and novel path by making use of the line graphs in graph theory. In particular, each node in a line graph corresponds to a unique edge in the original graph. Therefore, link prediction problems in the original graph can be equivalently solved as a node classification problem in its corresponding line graph, instead of a graph classification task.
  arXiv  Detail & Related papers  (2020-10-20T05:54:31Z)
• SF-GRASS: Solver-Free Graph Spectral Sparsification [16.313489255657203]
  This work introduces a solver-free approach (SF-GRASS) for spectral graph sparsification by leveraging emerging spectral graph coarsening and graph signal processing techniques. We show that the proposed method can produce a hierarchy of high-quality spectral sparsifiers in nearly-linear time for a variety of real-world, large-scale graphs and circuit networks.
  arXiv  Detail & Related papers  (2020-08-17T21:37:19Z)
• Spectral Image Segmentation with Global Appearance Modeling [0.913755431537592]
  We introduce a new spectral method for image segmentation that incorporates long range relationships for global appearance modeling. The approach combines two different graphs, one is a sparse graph that captures spatial relationships between nearby pixels and another is a dense graph that captures pairwise similarity between all pairs of pixels.
  arXiv  Detail & Related papers  (2020-06-11T16:21:54Z)
• Graphon Pooling in Graph Neural Networks [169.09536309161314]
  Graph neural networks (GNNs) have been used effectively in different applications involving the processing of signals on irregular structures modeled by graphs. We propose a new strategy for pooling and sampling on GNNs using graphons which preserves the spectral properties of the graph.
  arXiv  Detail & Related papers  (2020-03-03T21:04:20Z)
• Unsupervised Community Detection with a Potts Model Hamiltonian, an Efficient Algorithmic Solution, and Applications in Digital Pathology [1.6506888719932784]
  We propose a fast statistical down-sampling of input image pixels based on the respective color features, and a new iterative method to minimize the Potts model energy considering pixel to segment relationship. We demonstrate the application of our method in medical microscopy image segmentation; particularly, in segmenting renal glomerular micro-environment in renal pathology.
  arXiv  Detail & Related papers  (2020-02-05T01:20:28Z)

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.