Simple and Effective: Spatial Rescaling for Person Reidentification
Simple and Effective: Spatial Rescaling for Person Reidentification
复制标题
DOI：
10.1109/tnnls.2020.3027589
复制
发表时间：
2020-10
影响因子：
10.4
通讯作者：
Haoran Wang;L. Jiao;Shuyuan Yang;Lingling Li;Zexin Wang
中科院分区：
文献类型：
--
作者：
Haoran Wang;L. Jiao;Shuyuan Yang;Lingling Li;Zexin Wang
全局平均池(GAP)允许卷积神经网络(CNN)仅使用图像级标签来定位用于识别的区别性信息。虽然GAP有助于CNN注意到对象的最具区分性的特征，例如鸟头或一个人的袋子，但如果由于摄像机视点变化和某些任务中的类内变化而导致这些信息丢失，它可能会受到影响。为了避免这个问题，我们提出了一个新的模块来帮助CNN看到更多，即空间重新缩放(SPARS)层。它将要素地图激活之间的空间关系引入到模型中，引导模型关注要素地图中的大范围区域。实现简单，可以直接插入各种架构的CNN中。与重新识别(Re-ID)模型相比，SPARS层持续提高了性能。此外，基于不同归一化方法的新模块还展示了细粒度和通用图像分类基准的优越性。为了更好地理解，可视化方法显示了配备SPARS层时激活区域的变化。我们的代码在https://github.com/HRanWang/Spatial-Re-Scaling.上公开提供
Global average pooling (GAP) allows convolutional neural networks (CNNs) to localize discriminative information for recognition using only image-level labels. While GAP helps CNNs to attend to the most discriminative features of an object, e.g., head of a bird or one man’s bag, it may suffer if that information is missing due to camera viewpoint changes and intraclass variations in some tasks. To circumvent this issue, we propose one new module to help CNNs to see more, namely, Spatial Rescaling (SpaRs) layer. It introduces spatial relations among the feature map activations back to the model, guiding the model to focus on a broad area in the feature map. With simple implementation, it can be inserted into CNNs of various architectures directly. SpaRs layer consistently improves the performance over the reidentification (re-ID) models. Besides, the new module based on different normalization methods also demonstrates the superiority of fine-grained and general image classification benchmarks. The visualization method shows the changes in activated regions when equipped with the SpaRs layer for better understanding. Our code is publicly available at https://github.com/HRanWang/Spatial-Re-Scaling.