57,464 Hits in 4.0 sec

A Distributed Approach Toward Discriminative Distance Metric Learning

Jun Li, Xun Lin, Xiaoguang Rui, Yong Rui, Dacheng Tao
2015 IEEE Transactions on Neural Networks and Learning Systems  
In this paper, we propose a discriminative metric learning algorithm, and develop a distributed scheme learning metrics on moderate-sized subsets of data, and aggregating the results into a global solution  ...  The algorithm of the aggregated distance metric learning (ADML) scales well with the data size and can be controlled by the partition.  ...  DISCRIMINATIVE DISTANCE METRIC LEARNING We are concerned with constructing a Mahalanobis distance metric in the data feature space, which incorporates the discriminative information, i.e. the class membership  ... 
doi:10.1109/tnnls.2014.2377211 pmid:25532194 fatcat:5vj2u6fy75chnnyghjfoan7bwe

ECML: An Ensemble Cascade Metric Learning Mechanism towards Face Verification [article]

Fu Xiong, Yang Xiao, Zhiguo Cao, Yancheng Wang, Joey Tianyi Zhou, Jianxi Wu
2020 arXiv   pre-print
Considering the feature distribution characteristics of faces, a robust Mahalanobis metric learning method (RMML) with closed-form solution is additionally proposed.  ...  And, the proposed ensemble cascade metric learning mechanism is also applicable to other metric learning approaches.  ...  Metric learning aims to learn a discriminative distance function towards the specific task.  ... 
arXiv:2007.05720v1 fatcat:zz6wdqrwvbhsrm5bz55rfszanu

Principle of Learning Metrics for Exploratory Data Analysis

Samuel Kaski, Janne Sinkkonen
2004 Journal of VLSI Signal Processing Systems for Signal, Image and Video Technology  
We review two approaches: a clustering algorithm and another that is based on an explicitly generated metric.  ...  The learning of the metric is supervised by the auxiliary data, whereas the data analysis in the new metric is unsupervised.  ...  This and other results point to new approaches toward practical algorithms. Figure 1 : 1 Two SOMs modeling data distributed uniformly within a threedimensional cube.  ... 
doi:10.1023/b:vlsi.0000027483.39774.f8 fatcat:sy22ecjk3bcjnblhz3zkfeqbae

Local discriminative distance metrics ensemble learning

Yang Mu, Wei Ding, Dacheng Tao
2013 Pattern Recognition  
In this paper, we propose a new local discriminative distance metrics (LDDM) algorithm to learn multiple distance metrics from each training sample (a focal sample) and in the vicinity of that focal sample  ...  Those locally learned distance metrics are used to build local classifiers which are aligned in a probabilistic framework via ensemble learning.  ...  In this paper, we propose a multiple distance metric approach, the Local Discriminative Distance Metrics (LDDM) algorithm, from a new perspective.  ... 
doi:10.1016/j.patcog.2013.01.010 fatcat:oeoetwh6kzeb3f6ed6klfp4pcy

Generative Local Metric Learning for Nearest Neighbor Classification

Yung-Kyun Noh, Byoung-Tak Zhang, Daniel D. Lee
2018 IEEE Transactions on Pattern Analysis and Machine Intelligence  
As a byproduct, the asymptotic theoretical analysis in this work relates metric learning with dimensionality reduction, which was not understood from previous discriminative approaches.  ...  Conventional metric learning methods attempt to separate data distributions in a purely discriminative manner; here we show how to take advantage of information from parametric generative models.  ...  Previous work on metric learning for nearest neighbor classification has focused on a purely discriminative approach.  ... 
doi:10.1109/tpami.2017.2666151 pmid:28186880 fatcat:7sw3cvod6naxrplbi3q6krr6uq

Learning Discriminative Fisher Kernel for Image Retrieval

2013 KSII Transactions on Internet and Information Systems  
In this paper, we propose a similarity measure learning approach for image retrieval.  ...  We further propose a discriminative learning method for the similarity measure, i.e., encouraging the learned similarity to take a large value for a pair of images with the same label and to take a small  ...  A fast and scalable algorithm to learn a Mahalanobis distance [37] , which formulates the distance metric learning as a convex optimization problem DML-eig.  ... 
doi:10.3837/tiis.2013.03.007 fatcat:5t3dnxb25vbz3obtfc6oo5d46i

Cross-Entropy Adversarial View Adaptation for Person Re-identification [article]

Lin Wu, Richang Hong, Yang Wang, Meng Wang
2019 arXiv   pre-print
In this paper, we learn view-invariant subspace for person re-ID, and its corresponding similarity metric using an adversarial view adaptation approach.  ...  To determine the similarity value, the network is empowered with a similarity discriminator to promote features that are highly discriminant in distinguishing positive and negative pairs.  ...  As a comparison, our approach is able to address this issue by training a discriminative distance metric jointly with the view-invariant feature learning.  ... 
arXiv:1904.01755v2 fatcat:r64pqifmfzhebjcvy7wzbgkiuq

Learning Discriminative Metrics via Generative Models and Kernel Learning [article]

Yuan Shi, Yung-Kyun Noh, Fei Sha, Daniel D. Lee
2011 arXiv   pre-print
Metrics specifying distances between data points can be learned in a discriminative manner or from generative models.  ...  In this paper, we show how to unify generative and discriminative learning of metrics via a kernel learning framework.  ...  Ongoing work includes further investigations into more effective approaches to training nonlinear combinations of learned local metrics in a discriminative manner.  ... 
arXiv:1109.3940v1 fatcat:totbvwpmmjbyzpanvhacacsptu

Metric Learning-based Generative Adversarial Network [article]

Zi-Yi Dou
2017 arXiv   pre-print
The discriminator of MLGANs can dynamically learn an appropriate metric, rather than a static one, to measure the distance between generated samples and real samples.  ...  In this paper, we propose a novel framework to train GANs based on distance metric learning and we call it Metric Learning-based Gener- ative Adversarial Network (MLGAN).  ...  Compared to previous distance metric learning approaches, deep metric learning learns a nonlinear embedding of the data by using deep neural networks. The approach of Chopra et al.  ... 
arXiv:1711.02792v1 fatcat:wdyx46ti5zg35n65mvjlfocqca

Distance metric learning based on structural neighborhoods for dimensionality reduction and classification performance improvement [article]

Mostafa Razavi Ghods, Mohammad Hossein Moattar, Yahya Forghani
2020 arXiv   pre-print
Distance metric learning can be viewed as one of the fundamental interests in pattern recognition and machine learning, which plays a pivotal role in the performance of many learning methods.  ...  Using the local neighborhood relationships extracted from the manifold space, the proposed method learns the distance metric in a way which minimizes the distance between similar data and maximizes their  ...  distance metric learning approach.  ... 
arXiv:1902.03453v2 fatcat:blajv5catra4rbsruvabmjoaxa

Deep Divergence Learning [article]

Kubra Cilingir, Rachel Manzelli, Brian Kulis
2020 arXiv   pre-print
learning approaches for extending learning Euclidean distances to more general divergence measures such as divergences over distributions.  ...  existing deep metric learning approaches.  ...  Classical approaches to metric learning are generally focused on the linear regime, where one learns a linear mapping of the data and then applies the Euclidean distance in the mapped space for downstream  ... 
arXiv:2005.02612v1 fatcat:d4zwdlkw5ffnbjbx776jpikgou

On the Performance of Generative Adversarial Network by Limiting Mode Collapse for Malware Detection Systems

Acklyn Murray, Danda B. Rawat
2021 Sensors  
Generative adversarial network (GAN) has been regarded as a promising solution to many machine learning problems, and it comprises of a generator and discriminator, determining patterns and anomalies in  ...  Typically, a mode collapse occurs when a GAN fails to fit the set optimizations and leads to several instabilities in the generative model, diminishing the capability to generate new content regardless  ...  Birthday Paradox (BP), a metrics based on the principle used to measure the support size of the learned distribution by a GAN.  ... 
doi:10.3390/s22010264 pmid:35009810 pmcid:PMC8749644 fatcat:kl3uiq7ykbbcvcc6iciunfiqxa

Quality Aware Generative Adversarial Networks [article]

Parimala Kancharla, Sumohana S. Channappayya
2019 arXiv   pre-print
In this work, we show how a distance metric that is a variant of the Structural SIMilarity (SSIM) index (a popular full-reference image quality assessment algorithm), and a novel quality aware discriminator  ...  Generative Adversarial Networks (GANs) have become a very popular tool for implicitly learning high-dimensional probability distributions.  ...  GANs [1] pose the the problem of learning a high-dimensional distribution from data samples in a game-theoretic framework.  ... 
arXiv:1911.03149v1 fatcat:xf2p7bj6ibhurcm3y27abu5vf4

Adversarial Skill Networks: Unsupervised Robot Skill Learning from Video [article]

Oier Mees, Markus Merklinger, Gabriel Kalweit, Wolfram Burgard
2020 arXiv   pre-print
To this end, we propose a novel approach to learn a task-agnostic skill embedding space from unlabeled multi-view videos.  ...  We combine a metric learning loss, which utilizes temporal video coherence to learn a state representation, with an entropy regularized adversarial skill-transfer loss.  ...  The learned metric can then be used as a reward signal within a RL-setup by minimizing the distance to a visual demonstration.  ... 
arXiv:1910.09430v2 fatcat:755seey2lfebznbluzko6qrzdi

Distance Measure Machines [article]

Alain Rakotomamonjy, Maxime Berar
2018 arXiv   pre-print
This paper presents a distance-based discriminative framework for learning with probability distributions.  ...  Algorithmically, the proposed approach consists in computing a mapping based on pairwise dissimilarity where learning a linear decision function is amenable.  ...  Discriminating normal distributions with the mean ( , γ)-goodness of a dissimilarity function is a property that depends on the learning problem.  ... 
arXiv:1803.00250v3 fatcat:kh7t7uf3njfp7kxmhe3lxoxdkm
« Previous Showing results 1 — 15 out of 57,464 results