Deep metric learning for visual understanding : an overview of recent advances
Metric learning aims to learn a distance function to measure the similarity of samples, which plays an important role in many visual understanding applications. Generally, the optimal similarity functions for different visual understanding tasks are task specific because the distributions for data u...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/142292 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-142292 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1422922020-06-18T07:14:21Z Deep metric learning for visual understanding : an overview of recent advances Lu, Jiwen Hu, Junlin Zhou, Jie School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Neural Networks Visualization Metric learning aims to learn a distance function to measure the similarity of samples, which plays an important role in many visual understanding applications. Generally, the optimal similarity functions for different visual understanding tasks are task specific because the distributions for data used in different tasks are usually different. It is generally believed that learning a metric from training data can obtain more encouraging performances than handcrafted metrics [1]-[3], e.g., the Euclidean and cosine distances. A variety of metric learning methods have been proposed in the literature [2]-[5], and many of them have been successfully employed in visual understanding tasks such as face recognition [6], [7], image classification [2], [3], visual search [8], [9], visual tracking [10], [11], person reidentification [12], cross-modal matching [13], image set classification [14], and image-based geolocalization [15]-[17]. 2020-06-18T07:14:21Z 2020-06-18T07:14:21Z 2017 Journal Article Lu, J., Hu, J., & Zhou, J. (2017). Deep metric learning for visual understanding : an overview of recent advances. IEEE Signal Processing Magazine, 34(6), 76-84. doi:10.1109/MSP.2017.2732900 1053-5888 https://hdl.handle.net/10356/142292 10.1109/MSP.2017.2732900 2-s2.0-85044656490 6 34 76 84 en IEEE Signal Processing Magazine © 2017 IEEE. All rights reserved. |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Electrical and electronic engineering Neural Networks Visualization |
spellingShingle |
Engineering::Electrical and electronic engineering Neural Networks Visualization Lu, Jiwen Hu, Junlin Zhou, Jie Deep metric learning for visual understanding : an overview of recent advances |
description |
Metric learning aims to learn a distance function to measure the similarity of samples, which plays an important role in many visual understanding applications. Generally, the optimal similarity functions for different visual understanding tasks are task specific because the distributions for data used in different tasks are usually different. It is generally believed that learning a metric from training data can obtain more encouraging performances than handcrafted metrics [1]-[3], e.g., the Euclidean and cosine distances. A variety of metric learning methods have been proposed in the literature [2]-[5], and many of them have been successfully employed in visual understanding tasks such as face recognition [6], [7], image classification [2], [3], visual search [8], [9], visual tracking [10], [11], person reidentification [12], cross-modal matching [13], image set classification [14], and image-based geolocalization [15]-[17]. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Lu, Jiwen Hu, Junlin Zhou, Jie |
format |
Article |
author |
Lu, Jiwen Hu, Junlin Zhou, Jie |
author_sort |
Lu, Jiwen |
title |
Deep metric learning for visual understanding : an overview of recent advances |
title_short |
Deep metric learning for visual understanding : an overview of recent advances |
title_full |
Deep metric learning for visual understanding : an overview of recent advances |
title_fullStr |
Deep metric learning for visual understanding : an overview of recent advances |
title_full_unstemmed |
Deep metric learning for visual understanding : an overview of recent advances |
title_sort |
deep metric learning for visual understanding : an overview of recent advances |
publishDate |
2020 |
url |
https://hdl.handle.net/10356/142292 |
_version_ |
1681057242427686912 |