Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Tian, Qiwei, Lin, Chenhao, Zhao, Zhengyu, Li, Qian, Shen, Chao
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911103028559872
author Tian, Qiwei
Lin, Chenhao
Zhao, Zhengyu
Li, Qian
Shen, Chao
author_facet Tian, Qiwei
Lin, Chenhao
Zhao, Zhengyu
Li, Qian
Shen, Chao
contents 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 stronger 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. Codes are available at https://github.com/michaeltian108/CA-TRIDE.
format Preprint
id arxiv_https___arxiv_org_abs_2312_07364
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval
Tian, Qiwei
Lin, Chenhao
Zhao, Zhengyu
Li, Qian
Shen, Chao
Computer Vision and Pattern Recognition
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 stronger 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. Codes are available at https://github.com/michaeltian108/CA-TRIDE.
title Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.07364