IDEAL: Independent Domain Embedding Augmentation Learning
Many efforts have been devoted to designing sampling, mining, and weighting strategies in high-level deep metric learning (DML) loss objectives. However, little attention has been paid to low-level but essential data transformation. In this paper, we develop a novel mechanism, the independent domain...
Main Authors: | , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2021
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2105.10112 https://arxiv.org/abs/2105.10112 |
id |
ftdatacite:10.48550/arxiv.2105.10112 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2105.10112 2023-05-15T16:01:22+02:00 IDEAL: Independent Domain Embedding Augmentation Learning Chen, Zhiyuan Yao, Guang Ma, Wennan Xu, Lin 2021 https://dx.doi.org/10.48550/arxiv.2105.10112 https://arxiv.org/abs/2105.10112 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 Artificial Intelligence cs.AI FOS Computer and information sciences Article CreativeWork article Preprint 2021 ftdatacite https://doi.org/10.48550/arxiv.2105.10112 2022-03-10T14:24:23Z Many efforts have been devoted to designing sampling, mining, and weighting strategies in high-level deep metric learning (DML) loss objectives. However, little attention has been paid to low-level but essential data transformation. In this paper, we develop a novel mechanism, the independent domain embedding augmentation learning ({IDEAL}) method. It can simultaneously learn multiple independent embedding spaces for multiple domains generated by predefined data transformations. Our IDEAL is orthogonal to existing DML techniques and can be seamlessly combined with prior DML approaches for enhanced performance. Empirical results on visual retrieval tasks demonstrate the superiority of the proposed method. For example, the IDEAL improves the performance of MS loss by a large margin, 84.5\% $\rightarrow$ 87.1\% on Cars-196, and 65.8\% $\rightarrow$ 69.5\% on CUB-200 at Recall$@1$. Our IDEAL with MS loss also achieves the new state-of-the-art performance on three image retrieval benchmarks, \ie, \emph{Cars-196}, \emph{CUB-200}, and \emph{SOP}. It outperforms the most recent DML approaches, such as Circle loss and XBM, significantly. The source code and pre-trained models of our method will be available at\emph{\url{https://github.com/emdata-ailab/IDEAL}}. : 11 pages, 2 figures, 4 tables 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 Artificial Intelligence cs.AI FOS Computer and information sciences |
spellingShingle |
Computer Vision and Pattern Recognition cs.CV Artificial Intelligence cs.AI FOS Computer and information sciences Chen, Zhiyuan Yao, Guang Ma, Wennan Xu, Lin IDEAL: Independent Domain Embedding Augmentation Learning |
topic_facet |
Computer Vision and Pattern Recognition cs.CV Artificial Intelligence cs.AI FOS Computer and information sciences |
description |
Many efforts have been devoted to designing sampling, mining, and weighting strategies in high-level deep metric learning (DML) loss objectives. However, little attention has been paid to low-level but essential data transformation. In this paper, we develop a novel mechanism, the independent domain embedding augmentation learning ({IDEAL}) method. It can simultaneously learn multiple independent embedding spaces for multiple domains generated by predefined data transformations. Our IDEAL is orthogonal to existing DML techniques and can be seamlessly combined with prior DML approaches for enhanced performance. Empirical results on visual retrieval tasks demonstrate the superiority of the proposed method. For example, the IDEAL improves the performance of MS loss by a large margin, 84.5\% $\rightarrow$ 87.1\% on Cars-196, and 65.8\% $\rightarrow$ 69.5\% on CUB-200 at Recall$@1$. Our IDEAL with MS loss also achieves the new state-of-the-art performance on three image retrieval benchmarks, \ie, \emph{Cars-196}, \emph{CUB-200}, and \emph{SOP}. It outperforms the most recent DML approaches, such as Circle loss and XBM, significantly. The source code and pre-trained models of our method will be available at\emph{\url{https://github.com/emdata-ailab/IDEAL}}. : 11 pages, 2 figures, 4 tables |
format |
Article in Journal/Newspaper |
author |
Chen, Zhiyuan Yao, Guang Ma, Wennan Xu, Lin |
author_facet |
Chen, Zhiyuan Yao, Guang Ma, Wennan Xu, Lin |
author_sort |
Chen, Zhiyuan |
title |
IDEAL: Independent Domain Embedding Augmentation Learning |
title_short |
IDEAL: Independent Domain Embedding Augmentation Learning |
title_full |
IDEAL: Independent Domain Embedding Augmentation Learning |
title_fullStr |
IDEAL: Independent Domain Embedding Augmentation Learning |
title_full_unstemmed |
IDEAL: Independent Domain Embedding Augmentation Learning |
title_sort |
ideal: independent domain embedding augmentation learning |
publisher |
arXiv |
publishDate |
2021 |
url |
https://dx.doi.org/10.48550/arxiv.2105.10112 https://arxiv.org/abs/2105.10112 |
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.2105.10112 |
_version_ |
1766397260694814720 |