Abstract
Person re-identification has achieved great progress with deep convolutional neural networks. However, most previous methods focus on learning individual appearance feature embedding, and it is hard for the models to handle difficult situations with different illumination, large pose variance and occlusion. In this work, we take a step further and consider employing context information for person search. For a probe-gallery pair, we first propose a contextual instance expansion module, which employs a relative attention module to search and filter useful context information in the scene. We also build a graph learning framework to effectively employ context pairs to update target similarity. These two modules are built on top of a joint detection and instance feature learning framework, which improves the discriminativeness of the learned features. The proposed framework achieves state-of-the-art performance on two widely used person search datasets.
Abstract (translated)
深度卷积神经网络在人的再识别方面取得了很大的进展。然而,以往的方法大多侧重于学习个体的外观特征嵌入,而在不同的光照、较大的姿态变化和遮挡条件下,模型很难处理困难的情况。在这项工作中,我们进一步考虑使用上下文信息进行人员搜索。对于探针库对,我们首先提出了一个上下文实例扩展模块,该模块使用相对注意模块来搜索和过滤场景中有用的上下文信息。我们还构建了一个图形学习框架,有效地利用上下文对更新目标相似性。这两个模块构建在联合检测和实例特征学习框架之上,提高了所学特征的识别性。该框架在两个广泛使用的人搜索数据集上实现了最先进的性能。
URL
https://arxiv.org/abs/1904.01830