Collapse-aware Triplet Decoupling For Adversarially Robust Image Retrieval | Awesome Learning to Hash Add your paper to Learning2Hash

Awesome Learning to Hash

A Webpage dedicated to the latest research on Hash Function Learning. Maintained by Sean Moran.

Stay Updated

Contact Sean Moran about this survey or website. Made with Jekyll and Hyde.

Collapse-aware Triplet Decoupling For Adversarially Robust Image Retrieval

Qiwei Tian, Chenhao Lin, Zhengyu Zhao, Qian Li, Chao Shen . Arxiv 2023 – 0 citations

[Code] [Paper]   Search on Google Scholar   Search on Semantic Scholar
Datasets Distance Metric Learning Evaluation Image Retrieval Robustness

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.

Similar Work