English
Related papers

Related papers: Squared Earth Mover's Distance-based Loss for Trai…

200 papers

The demand of artificial intelligent adoption for condition-based maintenance strategy is astonishingly increased over the past few years. Intelligent fault diagnosis is one critical topic of maintenance solution for mechanical systems.…

Machine Learning · Computer Science 2022-06-17 Cheng Cheng , Beitong Zhou , Guijun Ma , Dongrui Wu , Ye Yuan

In many large-scale classification problems, classes are organized in a known hierarchy, typically represented as a tree expressing the inclusion of classes in superclasses. We introduce a loss for this type of supervised hierarchical…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Nicolas Urbani , Sylvain Rousseau , Yves Grandvalet , Leonardo Tanzi

Supervised training of deep neural nets typically relies on minimizing cross-entropy. However, in many domains, we are interested in performing well on metrics specific to the application. In this paper we propose a direct loss minimization…

Machine Learning · Computer Science 2016-06-03 Yang Song , Alexander G. Schwing , Richard S. Zemel , Raquel Urtasun

Unsupervised Deep Distance Metric Learning (UDML) aims to learn sample similarities in the embedding space from an unlabeled dataset. Traditional UDML methods usually use the triplet loss or pairwise loss which requires the mining of…

Computer Vision and Pattern Recognition · Computer Science 2020-09-10 Binh X. Nguyen , Binh D. Nguyen , Gustavo Carneiro , Erman Tjiputra , Quang D. Tran , Thanh-Toan Do

The Evidential regression network (ENet) estimates a continuous target and its predictive uncertainty without costly Bayesian model averaging. However, it is possible that the target is inaccurately predicted due to the gradient shrinkage…

Machine Learning · Computer Science 2021-12-20 Dongpin Oh , Bonggun Shin

Using class labels to represent class similarity is a typical approach to training deep hashing systems for retrieval; samples from the same or different classes take binary 1 or 0 similarity values. This similarity does not model the full…

Information Retrieval · Computer Science 2019-08-16 Heikki Arponen , Tom E Bishop

We introduce a new algorithm, called CDER, for supervised machine learning that merges the multi-scale geometric properties of Cover Trees with the information-theoretic properties of entropy. CDER applies to a training set of labeled…

Machine Learning · Computer Science 2018-01-23 Abraham Smith , Paul Bendich , John Harer , Alex Pieloch , Jay Hineman

Class-incremental learning of deep networks sequentially increases the number of classes to be classified. During training, the network has only access to data of one task at a time, where each task contains several classes. In this…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Lu Yu , Bartłomiej Twardowski , Xialei Liu , Luis Herranz , Kai Wang , Yongmei Cheng , Shangling Jui , Joost van de Weijer

Multiclass neural network classifiers are typically trained using cross-entropy loss but evaluated using metrics derived from the confusion matrix, such as Accuracy, $F_\beta$-Score, and Matthews Correlation Coefficient. This mismatch…

Machine Learning · Computer Science 2025-05-27 Deyuan Li , Taesoo Daniel Lee , Marynel Vázquez , Nathan Tsoi

The Earth movers distance (EMD) is a measure of distance between probability distributions which is at the heart of mass transportation theory. Recent research has shown that the EMD plays a crucial role in studying the potential impact of…

Computation · Statistics 2013-10-15 Kyle Treleaven , Emilio Frazzoli

The performance of unsupervised methods such as clustering depends on the choice of distance metric between features, or ground metric. Commonly, ground metrics are decided with heuristics or learned via supervised algorithms. However,…

Machine Learning · Computer Science 2025-01-13 Kira M. Düsterwald , Samo Hromadka , Makoto Yamada

With the development of convolutional neural networks (CNNs) in recent years, the network structure has become more and more complex and varied, and has achieved very good results in pattern recognition, image classification, object…

Computer Vision and Pattern Recognition · Computer Science 2019-04-29 Qiuyu Zhu , Pengju Zhang , Xin Ye

Quantifying how far the output of a learning algorithm is from its target is an essential task in machine learning. However, in quantum settings, the loss landscapes of commonly used distance metrics often produce undesirable outcomes such…

Quantum Physics · Physics 2022-07-07 Bobak Toussi Kiani , Giacomo De Palma , Milad Marvian , Zi-Wen Liu , Seth Lloyd

The goal of metric learning is to learn a function that maps samples to a lower-dimensional space where similar samples lie closer than dissimilar ones. Particularly, deep metric learning utilizes neural networks to learn such a mapping.…

Computer Vision and Pattern Recognition · Computer Science 2021-06-14 Jenny Seidenschwarz , Ismail Elezi , Laura Leal-Taixé

Compressed sensing can increase resolution, and decrease electron dose and scan time of electron microscope point-scan systems with minimal information loss. Building on a history of successful deep learning applications in compressed…

Image and Video Processing · Electrical Eng. & Systems 2019-10-28 Jeffrey M. Ede

In sequence prediction tasks like neural machine translation, training with cross-entropy loss often leads to models that overgeneralize and plunge into local optima. In this paper, we propose an extended loss function called \emph{dual…

Computation and Language · Computer Science 2021-04-20 Zuchao Li , Hai Zhao , Yingting Wu , Fengshun Xiao , Shu Jiang

Defining meaningful distances between samples in a dataset is a fundamental problem in machine learning. Optimal Transport (OT) lifts a distance between features (the "ground metric") to a geometrically meaningful distance between samples.…

Machine Learning · Statistics 2022-07-20 Geert-Jan Huizing , Laura Cantini , Gabriel Peyré

Deep metric learning (DML) is a cornerstone of many computer vision applications. It aims at learning a mapping from the input domain to an embedding space, where semantically similar objects are located nearby and dissimilar objects far…

Computer Vision and Pattern Recognition · Computer Science 2021-09-10 Artsiom Sanakoyeu , Pingchuan Ma , Vadim Tschernezki , Björn Ommer

In this work, a discriminatively learned CNN embedding is proposed for remote sensing image scene classification. Our proposed siamese network simultaneously computes the classification loss function and the metric learning loss function of…

Computer Vision and Pattern Recognition · Computer Science 2019-12-03 Wen Wang , Lijun Du , Yinxing Gao , Yanzhou Su , Feng Wang , Jian Cheng

Neural language models are probabilistic models of human text. They are predominantly trained using maximum likelihood estimation (MLE), which is equivalent to minimizing the forward cross-entropy between the empirical data distribution and…

Computation and Language · Computer Science 2024-02-07 Siyu Ren , Zhiyong Wu , Kenny Q. Zhu