paper-with-me

Papers

Unsupervised Image Semantic Segmentation through Superpixels and Graph Neural Networks

2022-10-21 · Moshe Eliasof, Nir Ben Zikri, Eran Treister

Unsupervised image segmentation is an important task in many real-world scenarios where labelled data is of scarce availability. In this paper we propose a novel approach that harnesses recent advances in unsupervised learning using a combination of Mutual Information Maximization (MIM), Neural Superpixel Segmentation and Graph Neural Networks (GNNs) in an end-to-end manner, an approach that has not been explored yet. We take advantage of the compact representation of superpixels and combine it with GNNs in order to learn strong and semantically meaningful representations of images. Specifically, we show that our GNN based approach allows to model interactions between distant pixels in the image and serves as a strong prior to existing CNNs for an improved accuracy. Our experiments reveal both the qualitative and quantitative advantages of our approach compared to current state-of-the-art methods over four popular datasets.

📄 PDF Abstract BibTeX arXiv:2210.11810

Code (0)

등록된 구현이 없습니다.

Tasks

Image SegmentationSegmentationSemantic SegmentationSuperpixelsUnsupervised Image SegmentationUnsupervised Semantic Segmentation

Similar Papers 제목 키워드 기반

Deep Superpixel Cut for Unsupervised Image Segmentation

2021-03-10 · Qinghong Lin, Weichan Zhong, Jianglin Lu

Image segmentation, one of the most critical vision tasks, has been studied for many years. Most of the early algorithms are unsupervised methods, which use hand-crafted features to divide the image into many regions. Re…

ClusteringImage SegmentationSegmentationSemantic Segmentation+2

Supervised and unsupervised segmentation using superpixels, model estimation, and Graph Cut.

2017-11-06 · SPIE Journal of Electronic Imaging 2017 11 · Jiří Borovec, Jan Švihlík, Jan Kybic, David Habart

Image segmentation is widely used as an initial phase of many image analysis tasks. It is often advantageous to first group pixels into compact, edge-respecting superpixels, because these reduce the size of the segmentat…

Image SegmentationSegmentationSemantic SegmentationSuperpixels

Unsupervised semantic discovery through visual patterns detection

2021-02-24 · Francesco Pelosin, Andrea Gasparetto, Andrea Albarelli, Andrea Torsello

We propose a new fast fully unsupervised method to discover semantic patterns. Our algorithm is able to hierarchically find visual categories and produce a segmentation mask where previous methods fail. Through the model…

ClusteringSuperpixels

SymmSLIC: Symmetry Aware Superpixel Segmentation and its Applications

2018-05-23 · Rajendra Nagar, Shanmuganathan Raman

Over-segmentation of an image into superpixels has become a useful tool for solving various problems in image processing and computer vision. Reflection symmetry is quite prevalent in both natural and man-made objects an…

Semantic SegmentationSuperpixels

Voxel Cloud Connectivity Segmentation - Supervoxels for Point Clouds

2013-06-01 · CVPR 2013 6 · Jeremie Papon, Alexey Abramov, Markus Schoeler, Florentin Worgotter

Unsupervised over-segmentation of an image into regions of perceptually similar pixels, known as superpixels, is a widely used preprocessing step in segmentation algorithms. Superpixel methods reduce the number of region…

ObjectSegmentationSuperpixels