Related papers: Unsupervised spectral learning
Unsupervised person re-identification (Re-ID) aims to match pedestrian images from different camera views in unsupervised setting. Existing methods for unsupervised person Re-ID are usually built upon the pseudo labels from clustering.…
Graph-based clustering has shown promising performance in many tasks. A key step of graph-based approach is the similarity graph construction. In general, learning graph in kernel space can enhance clustering accuracy due to the…
In this paper, we introduce a neural network framework for semi-supervised clustering (SSC) with pairwise (must-link or cannot-link) constraints. In contrast to existing approaches, we decompose SSC into two simpler classification…
Clustering is a well-known unsupervised machine learning approach capable of automatically grouping discrete sets of instances with similar characteristics. Constrained clustering is a semi-supervised extension to this process that can be…
To alleviate the cost of collecting and annotating large-scale point cloud datasets, we propose an unsupervised learning approach to learn features from unlabeled point cloud "3D object" dataset by using part contrasting and object…
In this paper, a similarity-driven cluster merging method is proposed for unsuper-vised fuzzy clustering. The cluster merging method is used to resolve the problem of cluster validation. Starting with an overspecified number of clusters in…
The task of labeling data for training deep neural networks is daunting and tedious, requiring millions of labels to achieve the current state-of-the-art results. Such reliance on large amounts of labeled data can be relaxed by exploiting…
Hyperspectral target detection is a pixel-level recognition problem. Given a few target samples, it aims to identify the specific target pixels such as airplane, vehicle, ship, from the entire hyperspectral image. In general, the background…
Deep clustering incorporates embedding into clustering to find a lower-dimensional space appropriate for clustering. In this paper, we propose a novel deep clustering framework with self-supervision using pairwise similarities (DCSS). The…
Semantic segmentation is a crucial step in many Earth observation tasks. Large quantity of pixel-level annotation is required to train deep networks for semantic segmentation. Earth observation techniques are applied to varieties of…
We consider spectral clustering algorithms for community detection under a general bipartite stochastic block model (SBM). A modern spectral clustering algorithm consists of three steps: (1) regularization of an appropriate adjacency or…
Hyperspectral image analysis has become an important topic widely researched by the remote sensing community. Classification and segmentation of such imagery help understand the underlying materials within a scanned scene, since…
Our previous experiments demonstrated that subsets collections of (short) documents (with several hundred entries) share a common normalized in some way eigenvalue spectrum of combinatorial Laplacian. Based on this insight, we propose a…
Clustering using neural networks has recently demonstrated promising performance in machine learning and computer vision applications. However, the performance of current approaches is limited either by unsupervised learning or their…
Drawing the quantum phase diagram of a many-body system in the parameter space of its Hamiltonian can be seen as a learning problem, which implies labelling the corresponding ground states according to some classification criterium that…
The objective of unsupervised domain adaptation is to leverage features from a labeled source domain and learn a classifier for an unlabeled target domain, with a similar but different data distribution. Most deep learning approaches to…
Consistency is a key property of all statistical procedures analyzing randomly sampled data. Surprisingly, despite decades of work, little is known about consistency of most clustering algorithms. In this paper we investigate consistency of…
We study supervised learning problems using clustering constraints to impose structure on either features or samples, seeking to help both prediction and interpretation. The problem of clustering features arises naturally in text…
This paper presents a novel unsupervised segmentation method for 3D medical images. Convolutional neural networks (CNNs) have brought significant advances in image segmentation. However, most of the recent methods rely on supervised…
Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coherent video data. We focus on feature learning from unlabeled…