Cluster analysis plays an indispensable role in machine learning and data mining. Learning
a good data representation is crucial for clustering algorithms. Recently, deep clustering …

The Gumbel-max trick is a method to draw a sample from a categorical distribution, given by
its unnormalized (log-) probabilities. Over the past years, the machine learning community …

Anomaly detection suffers from unbalanced data since anomalies are quite rare.
Synthetically generated anomalies are a solution to such ill or not fully defined data …

Conformational sampling of biomolecules using molecular dynamics simulations often
produces a large amount of high dimensional data that makes it difficult to interpret using …

We address the problem of web supervised learning, in particular for face attribute
classification. Web data suffers from image set noise, due to unrelated images that may be …

In recent years, with the great success of deep learning and especially deep unsupervised
learning, many deep architectural clustering methods, collectively known as deep clustering …

Deep clustering (DC) has become the state-of-the-art for unsupervised clustering. In
principle, DC represents a variety of unsupervised methods that jointly learn the underlying …

Distribution learning finds probability density functions from a set of data samples, whereas
clustering aims to group similar data points to form clusters. Although there are deep …

In this work, we propose a semi-supervised approach based on generative models to learn
both feature representations and categories in an end-to-end manner. The learning process …

Clustering has a long history in the computer vision community with a myriad of applications.
Clustering is a family of unsupervised machine learning techniques that group samples …