mlsanityData to 14 Oct 2026

A Sparse Graph Formulation for Efficient Spectral Image Segmentation

arXiv 2306.13166 ↗First posted 22 Jun 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 47 references that are in the map. First posted on arXiv 22 Jun 2023.

Builds on

19 of 47 references.

References · 19

  1. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  3. 2020Image Segmentation Using Deep Learning: A Surveycited by 660
  4. 2020A Survey on Visual Transformercited by 654
  5. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 455
  6. 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 230
  7. 2023Cut and Learn for Unsupervised Object Detection and Instance Segmentationcited by 187
  8. 2021PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clusteringcited by 163
  9. 2022Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localizationcited by 150
  10. 2022TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cutcited by 113
  11. 2019SegSort: Segmentation by Discriminative Sorting of Segmentscited by 96
  12. 2020Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clusteringcited by 61
7 more
  1. 2017W-Net: A Deep Model for Fully Unsupervised Image Segmentationcited by 57
  2. 2020Object Segmentation Without Labels with Large-Scale Generative Modelscited by 52
  3. 2021Finding an Unsupervised Image Segmenter in Each of Your Deep Generative Modelscited by 44
  4. 2022ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentationcited by 42
  5. 2018Scalable Spectral Clustering Using Random Binning Featurescited by 7
  6. 2021Direct Estimation of Appearance Models for Segmentationcited by 2
  7. 2020Spectral Image Segmentation with Global Appearance Modelingcited by 1

Built on by

Not cited yet.