Occluded person re-identification (Re-ID), the task of searching for the same person's images in occluded environments, has attracted lots of attention in the past decades. Recent approaches concentrate on improving performance on occluded data by data/feature augmentation or using extra models to predict occlusions. However, they ignore the imbalance problem in this task and can not fully utilize the information from the training data. To alleviate these two issues, we propose a simple yet effective method with Parallel Augmentation and Dual Enhancement (PADE), which is robust on both occluded and non-occluded data and does not require any auxiliary clues. First, we design a parallel augmentation mechanism (PAM) to generate more suitable occluded data to mitigate the negative effects of unbalanced data. Second, we propose the global and local dual enhancement strategy (DES) to promote the context information and details. Experimental results on three widely used occluded datasets and two non-occluded datasets validate the effectiveness of our method. The code is available at https://github.com/littleprince1121/PADE_Parallel_Augmentation_and_Dual_Enhancement_for_Occluded_Person_ReID

翻译：遮挡环境下行人重识别（Occluded Person Re-ID）旨在检索同一行人的图像，该任务在过去数十年间备受关注。现有方法侧重于通过数据/特征增强或利用额外模型预测遮挡来提升遮挡数据上的性能，但忽视了该任务中的不平衡问题，且无法充分利用训练数据中的信息。为缓解这两个问题，我们提出一种简洁高效的并行增强与双重增强方法（Parallel Augmentation and Dual Enhancement, PADE），该方法对遮挡与非遮挡数据均具有鲁棒性，且无需任何辅助线索。首先，我们设计并行增强机制（Parallel Augmentation Mechanism, PAM）生成更适配的遮挡数据，以减轻数据不平衡带来的不利影响；其次，提出全局与局部双重增强策略（Dual Enhancement Strategy, DES）以强化上下文信息与细节特征。在三个广泛使用的遮挡数据集和两个非遮挡数据集上的实验结果验证了该方法的有效性。代码已开源：https://github.com/littleprince1121/PADE_Parallel_Augmentation_and_Dual_Enhancement_for_Occluded_Person_ReID