Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval ...

• Main Authors: Tian, Qiwei, Lin, Chenhao, Zhao, Zhengyu, Li, Qian, Shen, Chao
• Format: Report
• Language: unknown
• Published: arXiv 2023
• Subjects: Computer Vision and Pattern Recognition cs.CV; FOS Computer and information sciences; DML
• Online Access: https://dx.doi.org/10.48550/arxiv.2312.07364; https://arxiv.org/abs/2312.07364

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. ...