Occluded person re-identification (Re-ID) aims to address the potential occlusion problem when matching occluded or holistic pedestrians from different camera views. Many methods use the background as artificial occlusion and rely on attention networks to exclude noisy interference. However, the significant discrepancy between simple background occlusion and realistic occlusion can negatively impact the generalization of the network. To address this issue, we propose a novel transformer-based Attention Disturbance and Dual-Path Constraint Network (ADP) to enhance the generalization of attention networks. Firstly, to imitate real-world obstacles, we introduce an Attention Disturbance Mask (ADM) module that generates an offensive noise, which can distract attention like a realistic occluder, as a more complex form of occlusion. Secondly, to fully exploit these complex occluded images, we develop a Dual-Path Constraint Module (DPC) that can obtain preferable supervision information from holistic images through dual-path interaction. With our proposed method, the network can effectively circumvent a wide variety of occlusions using the basic ViT baseline. Comprehensive experimental evaluations conducted on person re-ID benchmarks demonstrate the superiority of ADP over state-of-the-art methods.

翻译：遮挡行人重识别旨在解决不同摄像头视角下匹配遮挡或完整行人时可能出现的遮挡问题。许多方法将背景作为人工遮挡物，并依赖注意力网络排除噪声干扰。然而，简单背景遮挡与真实遮挡之间的显著差异会负面影响网络的泛化能力。为解决这一问题，我们提出了一种基于Transformer的新型注意力干扰与双路径约束网络，以增强注意力网络的泛化能力。首先，为模拟真实障碍物，我们引入了注意力干扰掩码模块，该模块生成一种攻击性噪声，能像真实遮挡物一样分散注意力，作为一种更复杂的遮挡形式。其次，为充分利用这些复杂的遮挡图像，我们开发了双路径约束模块，通过双路径交互从完整图像中获取更优的监督信息。通过所提出的方法，网络能够基于基础ViT基线有效规避多种遮挡。在行人重识别基准上进行的全面实验评估表明，ADP 优于当前最先进的方法。