Multi-Head Deep Metric Learning Using Global and Local Representations
Deep Metric Learning (DML) models often require strong local and global representations, however, effective integration of local and global features in DML model training is a challenge. DML models are often trained with specific loss functions, including pairwise-based and proxy-based losses. The p...
Main Authors: | , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2021
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2112.14327 https://arxiv.org/abs/2112.14327 |
id |
ftdatacite:10.48550/arxiv.2112.14327 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2112.14327 2023-05-15T16:01:08+02:00 Multi-Head Deep Metric Learning Using Global and Local Representations Ebrahimpour, Mohammad K. Qian, Gang Beach, Allison 2021 https://dx.doi.org/10.48550/arxiv.2112.14327 https://arxiv.org/abs/2112.14327 unknown arXiv Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 CC-BY Computer Vision and Pattern Recognition cs.CV Machine Learning cs.LG FOS Computer and information sciences Article CreativeWork article Preprint 2021 ftdatacite https://doi.org/10.48550/arxiv.2112.14327 2022-03-10T13:26:53Z Deep Metric Learning (DML) models often require strong local and global representations, however, effective integration of local and global features in DML model training is a challenge. DML models are often trained with specific loss functions, including pairwise-based and proxy-based losses. The pairwise-based loss functions leverage rich semantic relations among data points, however, they often suffer from slow convergence during DML model training. On the other hand, the proxy-based loss functions often lead to significant speedups in convergence during training, while the rich relations among data points are often not fully explored by the proxy-based losses. In this paper, we propose a novel DML approach to address these challenges. The proposed DML approach makes use of a hybrid loss by integrating the pairwise-based and the proxy-based loss functions to leverage rich data-to-data relations as well as fast convergence. Furthermore, the proposed DML approach utilizes both global and local features to obtain rich representations in DML model training. Finally, we also use the second-order attention for feature enhancement to improve accurate and efficient retrieval. In our experiments, we extensively evaluated the proposed DML approach on four public benchmarks, and the experimental results demonstrate that the proposed method achieved state-of-the-art performance on all benchmarks. : To appear in WACV 2022 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 |
Computer Vision and Pattern Recognition cs.CV Machine Learning cs.LG FOS Computer and information sciences |
spellingShingle |
Computer Vision and Pattern Recognition cs.CV Machine Learning cs.LG FOS Computer and information sciences Ebrahimpour, Mohammad K. Qian, Gang Beach, Allison Multi-Head Deep Metric Learning Using Global and Local Representations |
topic_facet |
Computer Vision and Pattern Recognition cs.CV Machine Learning cs.LG FOS Computer and information sciences |
description |
Deep Metric Learning (DML) models often require strong local and global representations, however, effective integration of local and global features in DML model training is a challenge. DML models are often trained with specific loss functions, including pairwise-based and proxy-based losses. The pairwise-based loss functions leverage rich semantic relations among data points, however, they often suffer from slow convergence during DML model training. On the other hand, the proxy-based loss functions often lead to significant speedups in convergence during training, while the rich relations among data points are often not fully explored by the proxy-based losses. In this paper, we propose a novel DML approach to address these challenges. The proposed DML approach makes use of a hybrid loss by integrating the pairwise-based and the proxy-based loss functions to leverage rich data-to-data relations as well as fast convergence. Furthermore, the proposed DML approach utilizes both global and local features to obtain rich representations in DML model training. Finally, we also use the second-order attention for feature enhancement to improve accurate and efficient retrieval. In our experiments, we extensively evaluated the proposed DML approach on four public benchmarks, and the experimental results demonstrate that the proposed method achieved state-of-the-art performance on all benchmarks. : To appear in WACV 2022 |
format |
Article in Journal/Newspaper |
author |
Ebrahimpour, Mohammad K. Qian, Gang Beach, Allison |
author_facet |
Ebrahimpour, Mohammad K. Qian, Gang Beach, Allison |
author_sort |
Ebrahimpour, Mohammad K. |
title |
Multi-Head Deep Metric Learning Using Global and Local Representations |
title_short |
Multi-Head Deep Metric Learning Using Global and Local Representations |
title_full |
Multi-Head Deep Metric Learning Using Global and Local Representations |
title_fullStr |
Multi-Head Deep Metric Learning Using Global and Local Representations |
title_full_unstemmed |
Multi-Head Deep Metric Learning Using Global and Local Representations |
title_sort |
multi-head deep metric learning using global and local representations |
publisher |
arXiv |
publishDate |
2021 |
url |
https://dx.doi.org/10.48550/arxiv.2112.14327 https://arxiv.org/abs/2112.14327 |
genre |
DML |
genre_facet |
DML |
op_rights |
Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 |
op_rightsnorm |
CC-BY |
op_doi |
https://doi.org/10.48550/arxiv.2112.14327 |
_version_ |
1766397120016809984 |