A tutorial on distance metric learning: Mathematical foundations, algorithms, experimental analysis, prospects and challenges
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 …
the data, which enhances the performance of similarity-based algorithms. This tutorial …
Embedding metric learning into an extreme learning machine for scene recognition
C Wang, G Peng, B De Baets - Expert Systems with Applications, 2022 - Elsevier
Metric learning can be very useful to improve the performance of a distance-dependent
classifier. However, separating metric learning from the classifier learning possibly …
classifier. However, separating metric learning from the classifier learning possibly …
Auto-attention mechanism for multi-view deep embedding clustering
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 …
workable method for handling data from several sources. For clustering multi-view data …
Few-shot contrastive learning for image classification and its application to insulator identification
L Li, W **, Y Huang - Applied Intelligence, 2022 - Springer
This paper presents a novel discriminative Few-shot learning architecture based on batch
compact loss. Currently, Convolutional Neural Network (CNN) has achieved reasonably …
compact loss. Currently, Convolutional Neural Network (CNN) has achieved reasonably …
A tutorial on distance metric learning: Mathematical foundations, algorithms, experimental analysis, prospects and challenges (with appendices on mathematical …
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 …
the data, which enhances the performance of similarity-based algorithms. This tutorial …
Improved generative adversarial network with deep metric learning for missing data imputation
MA Al-taezi, Y Wang, P Zhu, Q Hu, A Al-Badwi - Neurocomputing, 2024 - Elsevier
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 …
crucial for modeling machine learning algorithms. Although existing methods, such as …
Seismic characterization of individual geologic factors with disentangled features
Y Fei, H Cai, C Zhou, X He, J Liang, M Su, G Hu - Geophysics, 2024 - library.seg.org
Seismic attributes are critical in understanding geologic factors, such as sand body
configuration, lithology, and porosity. However, existing attributes typically reflect the …
configuration, lithology, and porosity. However, existing attributes typically reflect the …
A new similarity space tailored for supervised deep metric learning
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 …
we define a novel latent space obtained through an autoencoder. The new space, namely S …
A Simple Approach for Zero-Shot Learning based on Triplet Distribution Embeddings
V Chalumuri, B Nguyen - arxiv preprint arxiv:2103.15939, 2021 - arxiv.org
Given the semantic descriptions of classes, Zero-Shot Learning (ZSL) aims to recognize
unseen classes without labeled training data by exploiting semantic information, which …
unseen classes without labeled training data by exploiting semantic information, which …
[PDF][PDF] Machine Learning with Applications
We propose a new embedding method, named Quantile–Quantile Embedding (QQE), for
distribution transformation and manifold embedding with the ability to choose the …
distribution transformation and manifold embedding with the ability to choose the …