Seeds: Superpixels extracted via energy-driven sampling
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 …
same object. Many state-of-the-art superpixel algorithms rely on minimizing objective …
Guarantees for spectral clustering with fairness constraints
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 …
study a version of constrained SC in which we try to incorporate the fairness notion …
[PDF][PDF] A review on graph based segmentation
KS Camilus, VK Govindan - … Journal of Image, Graphics and Signal …, 2012 - mecs-press.org
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 …
few decades saw hundreds of research contributions in this field. However, the research on …
Constrained spectral clustering through affinity propagation
Z Lu, MA Carreira-Perpinan - 2008 IEEE Conference on …, 2008 - ieeexplore.ieee.org
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 …
has been successful to incorporate them into traditional clustering methods, such as K …
Combinatorial preconditioners and multilevel solvers for problems in computer vision and image processing
Several algorithms for problems including image segmentation, gradient inpainting and total
variation are based on solving symmetric diagonally dominant (SDD) linear systems. These …
variation are based on solving symmetric diagonally dominant (SDD) linear systems. These …
Training deep networks with structured layers by matrix backpropagation
C Ionescu, O Vantzos, C Sminchisescu - arXiv preprint arXiv:1509.07838, 2015 - arxiv.org
Deep neural network architectures have recently produced excellent results in a variety of
areas in artificial intelligence and visual recognition, well surpassing traditional shallow …
areas in artificial intelligence and visual recognition, well surpassing traditional shallow …
[PDF][PDF] A local spectral method for graphs: With applications to improving graph partitions and exploring data graphs locally
MW Mahoney, L Orecchia, NK Vishnoi - The Journal of Machine Learning …, 2012 - jmlr.org
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 …
fundamental features of an undirected graph, and as such they have found widespread use …
Spectral graph reduction for efficient image and streaming video segmentation
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 …
is a serious limitation especially in video segmentation. In this paper, we propose the use of …
Constrained 1-spectral clustering
SS Rangapuram, M Hein - Artificial Intelligence and Statistics, 2012 - proceedings.mlr.press
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 …
link constraints of instances. We present a generalization of the popular spectral clustering …