Person re-identification(Re-ID) has attracted increasing attention in the field of computer vision due to its great significance for the potential real-world applications. Profited from the success of convolutional neural networks(CNNs), existing multi-layer approaches leverage different scales of convolutional layers to learn more discriminative features, improving the Re-ID performance to some extent. However, these methods do not further explore whether all the scales of convolutional layers are positive for person re-identification. In this work, we propose a novel non-full multi-layer(NFML) network, which can jointly learn discriminative feature embeddings from positive multiple layers with the manner of combining global and local cues. Moreover, considering few works focus on how to effectively handle the feature maps, a simple yet effective feature progressing module named Pooling Batch Normalization(PBN), consisting of pooling, reduction and batch normalization operations, is introduced to optimize the model structure and further improve the Re-ID performance. Results on three mainstream benchmark datasets Market-1501, DukeMTMC-reID and CUHK03 demonstrate that our method can significantly boost the performances, outperforming the state-of-the-art methods.

人员重新识别（Re-ID）由于对潜在的现实应用具有重要意义，因此在计算机视觉领域引起了越来越多的关注。得益于卷积神经网络（CNN）的成功，现有的多层方法可以利用不同规模的卷积层来学习更多区分特征，从而在一定程度上提高Re-ID的性能。然而，这些方法没有进一步探讨卷积层的所有尺度对于人的重新识别是否都是正的。在这项工作中，我们提出了一种新颖的非完整多层（NFML）网络，该网络可以通过组合全局和局部提示的方式，从正多层中共同学习判别特征嵌入。此外，考虑到很少有作品关注如何有效处理要素图，引入了一个简单但有效的功能改进模块，称为合并批次归一化（PBN），该模块由合并，归约和批次归一化操作组成，以优化模型结构并进一步提高Re-ID性能。在三个主流基准数据集Market-1501，DukeMTMC-reID和CUHK03上的结果表明，我们的方法可以显着提高性能，优于最新方法。