Meta Generative Attack on Person Reidentification

2023/01/16 by A V Subramanyam, Subramanyam, A V
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Face recognition and analysis #Gait Recognition and Analysis #Video Surveillance and Tracking Methods

paper · pdf · doi:10.48550/arxiv.2301.06286

openalex publication_date 2023/01/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Adversarial attacks have been recently investigated in person re-identification. These attacks perform well under cross dataset or cross model setting. However, the challenges present in cross-dataset cross-model scenario does not allow these models to achieve similar accuracy. To this end, we propose our method with the goal of achieving better transferability against different models and across datasets. We generate a mask to obtain better performance across models and use meta learning to boost the generalizability in the challenging cross-dataset cross-model setting. Experiments on Market-1501, DukeMTMC-reID and MSMT-17 demonstrate favorable results compared to other attacks.

Related

• Learning to Learn Transferable Generative Attack for Person Re-Identification
• Beyond Universal Person Re-ID Attack
• Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification
• Debiased Dual-Invariant Defense for Adversarially Robust Person Re-Identification
• A Person Re-identification Data Augmentation Method with Adversarial Defense Effect