Abstract Spatial pooling is an important step in computer vision systems like Convolutional Neural Networks or the Bag-of-Words method. The spatial pooling purpose is to combine neighbouring descriptors to obtain a single descriptor for a given region (local or global). The resultant combined vector must be as discriminant as possible, in other words, must contain relevant information, while removing irrelevant and confusing details. Maximum and average are the most common aggregation functions used in the pooling step. To improve the aggregation of relevant information without degrading their discriminative power for image classification, we introduce a simple but effective scheme based on Ordered Weighted Average (OWA) aggregation operators. We present a method to learn the weights of the OWA aggregation operator in a Bag-of-Words framework and in Convolutional Neural Networks, and provide an extensive evaluation showing that OWA based pooling outperforms classical aggregation operators.

中文翻译：

---

学习图像分类中的有序池化权重

摘要 空间池化是计算机视觉系统（如卷积神经网络或词袋方法）中的重要步骤。空间池化的目的是组合相邻的描述符以获得给定区域（局部或全局）的单个描述符。得到的组合向量必须尽可能具有判别性，换句话说，必须包含相关信息，同时去除不相关和令人困惑的细节。最大值和平均值是池化步骤中最常用的聚合函数。为了在不降低图像分类判别力的情况下改进相关信息的聚合，我们引入了一种基于有序加权平均 (OWA) 聚合算子的简单而有效的方案。