ProcSim: Proxy-based Confidence for Robust Similarity Learning ...
Deep Metric Learning (DML) methods aim at learning an embedding space in which distances are closely related to the inherent semantic similarity of the inputs. Previous studies have shown that popular benchmark datasets often contain numerous wrong labels, and DML methods are susceptible to them. In...
Main Authors: | , , , |
---|---|
Format: | Report |
Language: | unknown |
Published: |
arXiv
2023
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2311.00668 https://arxiv.org/abs/2311.00668 |
id |
ftdatacite:10.48550/arxiv.2311.00668 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2311.00668 2023-12-31T10:06:16+01:00 ProcSim: Proxy-based Confidence for Robust Similarity Learning ... Barbany, Oriol Lin, Xiaofan Bastan, Muhammet Dhua, Arnab 2023 https://dx.doi.org/10.48550/arxiv.2311.00668 https://arxiv.org/abs/2311.00668 unknown arXiv arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences CreativeWork Preprint article Article 2023 ftdatacite https://doi.org/10.48550/arxiv.2311.00668 2023-12-01T10:26:52Z Deep Metric Learning (DML) methods aim at learning an embedding space in which distances are closely related to the inherent semantic similarity of the inputs. Previous studies have shown that popular benchmark datasets often contain numerous wrong labels, and DML methods are susceptible to them. Intending to study the effect of realistic noise, we create an ontology of the classes in a dataset and use it to simulate semantically coherent labeling mistakes. To train robust DML models, we propose ProcSim, a simple framework that assigns a confidence score to each sample using the normalized distance to its class representative. The experimental results show that the proposed method achieves state-of-the-art performance on the DML benchmark datasets injected with uniform and the proposed semantically coherent noise. ... : Accepted to the algorithms track of WACV 2024 ... Report 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 FOS Computer and information sciences |
spellingShingle |
Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences Barbany, Oriol Lin, Xiaofan Bastan, Muhammet Dhua, Arnab ProcSim: Proxy-based Confidence for Robust Similarity Learning ... |
topic_facet |
Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences |
description |
Deep Metric Learning (DML) methods aim at learning an embedding space in which distances are closely related to the inherent semantic similarity of the inputs. Previous studies have shown that popular benchmark datasets often contain numerous wrong labels, and DML methods are susceptible to them. Intending to study the effect of realistic noise, we create an ontology of the classes in a dataset and use it to simulate semantically coherent labeling mistakes. To train robust DML models, we propose ProcSim, a simple framework that assigns a confidence score to each sample using the normalized distance to its class representative. The experimental results show that the proposed method achieves state-of-the-art performance on the DML benchmark datasets injected with uniform and the proposed semantically coherent noise. ... : Accepted to the algorithms track of WACV 2024 ... |
format |
Report |
author |
Barbany, Oriol Lin, Xiaofan Bastan, Muhammet Dhua, Arnab |
author_facet |
Barbany, Oriol Lin, Xiaofan Bastan, Muhammet Dhua, Arnab |
author_sort |
Barbany, Oriol |
title |
ProcSim: Proxy-based Confidence for Robust Similarity Learning ... |
title_short |
ProcSim: Proxy-based Confidence for Robust Similarity Learning ... |
title_full |
ProcSim: Proxy-based Confidence for Robust Similarity Learning ... |
title_fullStr |
ProcSim: Proxy-based Confidence for Robust Similarity Learning ... |
title_full_unstemmed |
ProcSim: Proxy-based Confidence for Robust Similarity Learning ... |
title_sort |
procsim: proxy-based confidence for robust similarity learning ... |
publisher |
arXiv |
publishDate |
2023 |
url |
https://dx.doi.org/10.48550/arxiv.2311.00668 https://arxiv.org/abs/2311.00668 |
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.2311.00668 |
_version_ |
1786838242427928576 |