Patch-Based Deep Unsupervised Image Segmentation Using Graph Cuts

Isaac Wasserman, Jeová Farias Sales Rocha Neto

2025

Abstract

Unsupervised image segmentation seeks to group semantic patterns in an image without the use of human annotation. Similarly, image clustering searches for groupings of images based on their semantic content. Traditionally, both problems have drawn from sound mathematical concepts to produce concrete applications. With the emergence of deep learning, the scientific community turned its attention to complex neural network-based solvers that achieved impressive results in those domains but rarely leveraged the advances made by classical methods. In this work, we propose a patch-based unsupervised image segmentation strategy that uses the algorithmic strength of classical graph-based methods to enhance unsupervised feature extraction from deep clustering. We show that a simple convolutional neural network, trained to classify image patches and iteratively regularized using graph cuts, can be transformed into a state-of-the-art, fully-convolutional, unsupervised, pixel-level segmenter. Furthermore, we demonstrate that this is the ideal setting for leveraging the patch-level pairwise features generated by vision transformer models. Our results on real image data demonstrate the effectiveness of our proposed methodology.

Paper Citation

in Harvard Style

Wasserman I. and Neto J. (2025). Patch-Based Deep Unsupervised Image Segmentation Using Graph Cuts. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 102-112. DOI: 10.5220/0013151300003912

in Bibtex Style

@conference{visapp25,
author={Isaac Wasserman and Jeová Neto},
title={Patch-Based Deep Unsupervised Image Segmentation Using Graph Cuts},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2025},
pages={102-112},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013151300003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Patch-Based Deep Unsupervised Image Segmentation Using Graph Cuts
SN - 978-989-758-728-3
AU - Wasserman I.
AU - Neto J.
PY - 2025
SP - 102
EP - 112
DO - 10.5220/0013151300003912
PB - SciTePress