Comparison of distance metric learning methods against label noise for fine-grained recognition

2021 ◽  
Author(s):  
Alper Kayabasi ◽  
Kaan Karaman ◽  
Ibrahim Batuhan Akkaya
Keyword(s):  
Metric Learning ◽  
Distance Metric Learning ◽  
Distance Metric ◽  
Learning Methods ◽  
Label Noise ◽  
Fine Grained

scholarly journals Learning Mahalanobis Distance Metric: Considering Instance Disturbance Helps

2017 ◽  
Author(s):  
Han-Jia Ye ◽  
De-Chuan Zhan ◽  
Xue-Min Si ◽  
Yuan Jiang
Keyword(s):  
Mahalanobis Distance ◽  
Side Information ◽  
Metric Learning ◽  
Learning Approach ◽  
Distance Metric Learning ◽  
Distance Metric ◽  
Information Utilization ◽  
Learning Methods ◽  
Feature Weights ◽  
Distance Computation

Mahalanobis distance metric takes feature weights and correlation into account in the distance computation, which can improve the performance of many similarity/dissimilarity based methods, such as kNN. Most existing distance metric learning methods obtain metric based on the raw features and side information but neglect the reliability of them. Noises or disturbances on instances will make changes on their relationships, so as to affect the learned metric.In this paper, we claim that considering disturbance of instances may help the distance metric learning approach get a robust metric, and propose the Distance metRIc learning Facilitated by disTurbances (DRIFT) approach. In DRIFT, the noise or the disturbance of each instance is learned. Therefore, the distance between each pair of (noisy) instances can be better estimated, which facilitates side information utilization and metric learning.Experiments on prediction and visualization clearly indicate the effectiveness of the proposed approach.

An Overview and Empirical Comparison of Distance Metric Learning Methods

2017 ◽  
Vol 47 (3) ◽  
pp. 612-625 ◽  
Author(s):  
Panagiotis Moutafis ◽  
Mengjun Leng ◽  
Ioannis A. Kakadiaris
Keyword(s):  
Metric Learning ◽  
Distance Metric Learning ◽  
Distance Metric ◽  
Empirical Comparison ◽  
Learning Methods

Re-KISSME: A robust resampling scheme for distance metric learning in the presence of label noise

2019 ◽  
Vol 330 ◽  
pp. 138-150 ◽  
Author(s):  
Fanxia Zeng ◽  
Wensheng Zhang ◽  
Siheng Zhang ◽  
Nan Zheng
Keyword(s):  
Metric Learning ◽  
Distance Metric Learning ◽  
Distance Metric ◽  
Label Noise

scholarly journals Unsupervised Metric Learning with Synthetic Examples

2020 ◽  
Vol 34 (04) ◽  
pp. 3834-3841
Author(s):  
Ujjal Kr Dutta ◽  
Mehrtash Harandi ◽  
C. Chandra Sekhar
Keyword(s):  
Conditional Probability ◽  
Metric Learning ◽  
Large Datasets ◽  
Unlabeled Data ◽  
Distance Metric Learning ◽  
Distance Metric ◽  
Learning Methods ◽  
Stochastic Formulation ◽  
Class Labels ◽  
Measure Of Uncertainty

Distance Metric Learning (DML) involves learning an embedding that brings similar examples closer while moving away dissimilar ones. Existing DML approaches make use of class labels to generate constraints for metric learning. In this paper, we address the less-studied problem of learning a metric in an unsupervised manner. We do not make use of class labels, but use unlabeled data to generate adversarial, synthetic constraints for learning a metric inducing embedding. Being a measure of uncertainty, we minimize the entropy of a conditional probability to learn the metric. Our stochastic formulation scales well to large datasets, and performs competitive to existing metric learning methods.

scholarly journals Distance metric learning for graph structured data

2021 ◽  
Author(s):  
Tomoki Yoshida ◽  
Ichiro Takeuchi ◽  
Masayuki Karasuyama
Keyword(s):  
Metric Learning ◽  
Structured Data ◽  
Distance Metric Learning ◽  
Distance Metric
Sign in / Sign up

Export Citation Format

Share Document