Abstract
Person re-identification is indeed a challenging visual recognition task due to the critical issues of human pose variation, human body occlusion, camera view variation, etc. To address this, most of the state-of-the-art approaches are proposed based on deep convolutional neural network (CNN), being leveraged by its strong feature learning power and classification boundary fitting capacity. Although the vital role towards person re-identification, how to build effective CNN baseline model has not been well studied yet. To answer this open question, we propose 3 good practices in this paper from the perspectives of adjusting CNN architecture and training procedure. In particular, they are adding batch normalization after the global pooling layer, executing identity categorization directly using only one fully-connected, and using Adam as optimizer. The extensive experiments on 3 widely-used benchmark datasets demonstrate that, our propositions essentially facilitate the CNN baseline model to achieve the state-of-the-art performance without any other high-level domain knowledge or low-level technical trick.
Abstract (translated)
由于人体姿势变化,人体遮挡,摄像机视图变化等的关键问题,人员重新识别确实是具有挑战性的视觉识别任务。为了解决这个问题,大多数最先进的方法是基于提出的。深度卷积神经网络(CNN),其强大的特征学习能力和分类边界拟合能力得到充分利用。虽然对人的重新识别至关重要,但如何建立有效的CNN基线模型尚未得到很好的研究。为了回答这个悬而未决的问题,我们从调整CNN架构和培训程序的角度提出了本文中的3个良好实践。特别是,他们在全局池层之后添加批量规范化,仅使用一个完全连接的直接执行身份分类,并使用Adam作为优化器。对3个广泛使用的基准数据集进行的大量实验表明,我们的命题基本上促进了CNN基线模型在没有任何其他高级领域知识或低级技术诀窍的情况下实现最先进的性能。
URL
https://arxiv.org/abs/1807.11042