UnSegGNet: Unsupervised Image Segmentation using Graph Neural Networks

TL;DR

UnSegGNet introduces an unsupervised image segmentation approach that combines pretrained vision transformers with graph neural networks and modularity optimization, achieving competitive results without labeled data.

Contribution

It presents a novel unsupervised segmentation method leveraging graph neural networks and vision transformers, eliminating the need for labeled training data.

Findings

Demonstrates competitive performance on benchmark datasets.

Effectively delineates meaningful image boundaries.

Applicable to medical imaging and remote sensing.

Abstract

Image segmentation, the process of partitioning an image into meaningful regions, plays a pivotal role in computer vision and medical imaging applications. Unsupervised segmentation, particularly in the absence of labeled data, remains a challenging task due to the inter-class similarity and variations in intensity and resolution. In this study, we extract high-level features of the input image using pretrained vision transformer. Subsequently, the proposed method leverages the underlying graph structures of the images, seeking to discover and delineate meaningful boundaries using graph neural networks and modularity based optimization criteria without relying on pre-labeled training data. Experimental results on benchmark datasets demonstrate the effectiveness and versatility of the proposed approach, showcasing competitive performance compared to the state-of-the-art unsupervised segmentation methods. This research contributes to the broader field of unsupervised medical imaging and computer vision by presenting an innovative methodology for image segmentation that aligns with real-world challenges. The proposed method holds promise for diverse applications, including medical imaging, remote sensing, and object recognition, where labeled data may be scarce or unavailable. The github repository of the code is available on [https://github.com/ksgr5566/unseggnet]