Superpixel algorithms aim to over-segment the image by grouping pixels that belong to the
same object. Many state-of-the-art superpixel algorithms rely on minimizing objective …

Given the widespread popularity of spectral clustering (SC) for partitioning graph data, we
study a version of constrained SC in which we try to incorporate the fairness notion …

Image segmentation plays a crucial role in effective understanding of digital images. Past
few decades saw hundreds of research contributions in this field. However, the research on …

Pairwise constraints specify whether or not two samples should be in one cluster. Although it
has been successful to incorporate them into traditional clustering methods, such as K …

Several algorithms for problems including image segmentation, gradient inpainting and total
variation are based on solving symmetric diagonally dominant (SDD) linear systems. These …

Deep neural network architectures have recently produced excellent results in a variety of
areas in artificial intelligence and visual recognition, well surpassing traditional shallow …

The second eigenvalue of the Laplacian matrix and its associated eigenvector are
fundamental features of an undirected graph, and as such they have found widespread use …

We present a modification of “Normalized Cuts” to incorporate priors which can be used for
constrained image segmentation. Compared to previous generalizations of “Normalized …

Computational and memory costs restrict spectral techniques to rather small graphs, which
is a serious limitation especially in video segmentation. In this paper, we propose the use of …

An important form of prior information in clustering comes in the form of cannot-link and must-
link constraints of instances. We present a generalization of the popular spectral clustering …