A Simple and Effective Framework for Pairwise Deep Metric Learning
Deep metric learning (DML) has received much attention in deep learning due to its wide applications in computer vision. Previous studies have focused on designing complicated losses and hard example mining methods, which are mostly heuristic and lack of theoretical understanding. In this paper, we...
Main Authors: | , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2019
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.1912.11194 https://arxiv.org/abs/1912.11194 |
id |
ftdatacite:10.48550/arxiv.1912.11194 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.1912.11194 2023-05-15T16:01:41+02:00 A Simple and Effective Framework for Pairwise Deep Metric Learning Qi, Qi Yan, Yan Wang, Xiaoyu Yang, Tianbao 2019 https://dx.doi.org/10.48550/arxiv.1912.11194 https://arxiv.org/abs/1912.11194 unknown arXiv arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ Machine Learning cs.LG Computer Vision and Pattern Recognition cs.CV Machine Learning stat.ML FOS Computer and information sciences Article CreativeWork article Preprint 2019 ftdatacite https://doi.org/10.48550/arxiv.1912.11194 2022-03-10T16:33:19Z Deep metric learning (DML) has received much attention in deep learning due to its wide applications in computer vision. Previous studies have focused on designing complicated losses and hard example mining methods, which are mostly heuristic and lack of theoretical understanding. In this paper, we cast DML as a simple pairwise binary classification problem that classifies a pair of examples as similar or dissimilar. It identifies the most critical issue in this problem--imbalanced data pairs. To tackle this issue, we propose a simple and effective framework to sample pairs in a batch of data for updating the model. The key to this framework is to define a robust loss for all pairs over a mini-batch of data, which is formulated by distributionally robust optimization. The flexibility in constructing the uncertainty decision set of the dual variable allows us to recover state-of-the-art complicated losses and also to induce novel variants. Empirical studies on several benchmark data sets demonstrate that our simple and effective method outperforms the state-of-the-art results. Codes are available at: https://github.com/qiqi-helloworld/A-Simple-and-Effective-Framework-for-Pairewise-Distance-Metric-Learning : 16 pages, 5 figures Article in Journal/Newspaper DML DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Machine Learning cs.LG Computer Vision and Pattern Recognition cs.CV Machine Learning stat.ML FOS Computer and information sciences |
spellingShingle |
Machine Learning cs.LG Computer Vision and Pattern Recognition cs.CV Machine Learning stat.ML FOS Computer and information sciences Qi, Qi Yan, Yan Wang, Xiaoyu Yang, Tianbao A Simple and Effective Framework for Pairwise Deep Metric Learning |
topic_facet |
Machine Learning cs.LG Computer Vision and Pattern Recognition cs.CV Machine Learning stat.ML FOS Computer and information sciences |
description |
Deep metric learning (DML) has received much attention in deep learning due to its wide applications in computer vision. Previous studies have focused on designing complicated losses and hard example mining methods, which are mostly heuristic and lack of theoretical understanding. In this paper, we cast DML as a simple pairwise binary classification problem that classifies a pair of examples as similar or dissimilar. It identifies the most critical issue in this problem--imbalanced data pairs. To tackle this issue, we propose a simple and effective framework to sample pairs in a batch of data for updating the model. The key to this framework is to define a robust loss for all pairs over a mini-batch of data, which is formulated by distributionally robust optimization. The flexibility in constructing the uncertainty decision set of the dual variable allows us to recover state-of-the-art complicated losses and also to induce novel variants. Empirical studies on several benchmark data sets demonstrate that our simple and effective method outperforms the state-of-the-art results. Codes are available at: https://github.com/qiqi-helloworld/A-Simple-and-Effective-Framework-for-Pairewise-Distance-Metric-Learning : 16 pages, 5 figures |
format |
Article in Journal/Newspaper |
author |
Qi, Qi Yan, Yan Wang, Xiaoyu Yang, Tianbao |
author_facet |
Qi, Qi Yan, Yan Wang, Xiaoyu Yang, Tianbao |
author_sort |
Qi, Qi |
title |
A Simple and Effective Framework for Pairwise Deep Metric Learning |
title_short |
A Simple and Effective Framework for Pairwise Deep Metric Learning |
title_full |
A Simple and Effective Framework for Pairwise Deep Metric Learning |
title_fullStr |
A Simple and Effective Framework for Pairwise Deep Metric Learning |
title_full_unstemmed |
A Simple and Effective Framework for Pairwise Deep Metric Learning |
title_sort |
simple and effective framework for pairwise deep metric learning |
publisher |
arXiv |
publishDate |
2019 |
url |
https://dx.doi.org/10.48550/arxiv.1912.11194 https://arxiv.org/abs/1912.11194 |
genre |
DML |
genre_facet |
DML |
op_rights |
arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
op_doi |
https://doi.org/10.48550/arxiv.1912.11194 |
_version_ |
1766397446734217216 |