Distance metric learning is a branch of machine learning that aims to learn distances from
the data, which enhances the performance of similarity-based algorithms. This tutorial …

Metric learning can be very useful to improve the performance of a distance-dependent
classifier. However, separating metric learning from the classifier learning possibly …

In several fields, deep learning has achieved tremendous success. Multi-view learning is a
workable method for handling data from several sources. For clustering multi-view data …

Distance metric learning is a branch of machine learning that aims to learn distances from
the data, which enhances the performance of similarity-based algorithms. This tutorial …

This paper presents a novel discriminative Few-shot learning architecture based on batch
compact loss. Currently, Convolutional Neural Network (CNN) has achieved reasonably …

Incomplete data are ubiquitous in real-world computer vision tasks. Imputing missing data is
crucial for modeling machine learning algorithms. Although existing methods, such as …

Seismic attributes are critical in understanding geologic factors, such as sand body
configuration, lithology, and porosity. However, existing attributes typically reflect the …

We propose a novel deep metric learning method. Differently from many works in this area,
we define a novel latent space obtained through an autoencoder. The new space, namely S …

Given the semantic descriptions of classes, Zero-Shot Learning (ZSL) aims to recognize
unseen classes without labeled training data by exploiting semantic information, which …

No presente trabalho, propomos um novo método de aprendizagem métrica profunda que
diferentemente de muitos trabalhos nesta área, define um novo espaço latente obtido por …