Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval ...
Adversarial training has achieved substantial performance in defending image retrieval against adversarial examples. However, existing studies in deep metric learning (DML) still suffer from two major limitations: weak adversary and model collapse. In this paper, we address these two limitations by...
Main Authors: | , , , , |
---|---|
Format: | Report |
Language: | unknown |
Published: |
arXiv
2023
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2312.07364 https://arxiv.org/abs/2312.07364 |
id |
ftdatacite:10.48550/arxiv.2312.07364 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2312.07364 2024-03-31T07:52:28+00:00 Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval ... Tian, Qiwei Lin, Chenhao Zhao, Zhengyu Li, Qian Shen, Chao 2023 https://dx.doi.org/10.48550/arxiv.2312.07364 https://arxiv.org/abs/2312.07364 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 article Preprint Article CreativeWork 2023 ftdatacite https://doi.org/10.48550/arxiv.2312.07364 2024-03-04T13:07:01Z Adversarial training has achieved substantial performance in defending image retrieval against adversarial examples. However, existing studies in deep metric learning (DML) still suffer from two major limitations: weak adversary and model collapse. In this paper, we address these two limitations by proposing collapse-aware triplet decoupling (CA-TRIDE). Specifically, TRIDE yields a strong adversary by spatially decoupling the perturbation targets into the anchor and the other candidates. Furthermore, CA prevents the consequential model collapse, based on a novel metric, collapseness, which is incorporated into the optimization of perturbation. We also identify two drawbacks of the existing robustness metric in image retrieval and propose a new metric for a more reasonable robustness evaluation. Extensive experiments on three datasets demonstrate that CA-TRIDE outperforms existing defense methods in both conventional and new metrics. ... 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 Tian, Qiwei Lin, Chenhao Zhao, Zhengyu Li, Qian Shen, Chao Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval ... |
topic_facet |
Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences |
description |
Adversarial training has achieved substantial performance in defending image retrieval against adversarial examples. However, existing studies in deep metric learning (DML) still suffer from two major limitations: weak adversary and model collapse. In this paper, we address these two limitations by proposing collapse-aware triplet decoupling (CA-TRIDE). Specifically, TRIDE yields a strong adversary by spatially decoupling the perturbation targets into the anchor and the other candidates. Furthermore, CA prevents the consequential model collapse, based on a novel metric, collapseness, which is incorporated into the optimization of perturbation. We also identify two drawbacks of the existing robustness metric in image retrieval and propose a new metric for a more reasonable robustness evaluation. Extensive experiments on three datasets demonstrate that CA-TRIDE outperforms existing defense methods in both conventional and new metrics. ... |
format |
Report |
author |
Tian, Qiwei Lin, Chenhao Zhao, Zhengyu Li, Qian Shen, Chao |
author_facet |
Tian, Qiwei Lin, Chenhao Zhao, Zhengyu Li, Qian Shen, Chao |
author_sort |
Tian, Qiwei |
title |
Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval ... |
title_short |
Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval ... |
title_full |
Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval ... |
title_fullStr |
Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval ... |
title_full_unstemmed |
Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval ... |
title_sort |
collapse-aware triplet decoupling for adversarially robust image retrieval ... |
publisher |
arXiv |
publishDate |
2023 |
url |
https://dx.doi.org/10.48550/arxiv.2312.07364 https://arxiv.org/abs/2312.07364 |
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.2312.07364 |
_version_ |
1795031619726213120 |