Guangdong University of Technology, Guangzhou 510006, China; Hasselt University, Martelarenlaan 42, Hasselt 3500, Belgium.
Guangdong University of Technology, Guangzhou 510006, China.
Neural Netw. 2020 Oct;130:1-10. doi: 10.1016/j.neunet.2020.06.010. Epub 2020 Jun 24.
Activated hidden units in convolutional neural networks (CNNs), known as feature maps, dominate image representation, which is compact and discriminative. For ultra-large datasets, high dimensional feature maps in float format not only result in high computational complexity, but also occupy massive memory space. To this end, a new image representation by aggregating convolution kernels (ACK) is proposed, where some convolution kernels capturing certain patterns are activated. The top-n index numbers of the convolution kernels are extracted directly as image representation in discrete integer values, which rebuild relationship between convolution kernels and image. Furthermore, a distance measurement is defined from the perspective of ordered sets to calculate position-sensitive similarities between image representations. Extensive experiments conducted on Oxford Buildings, Paris, and Holidays, etc., manifest that the proposed ACK achieves competitive performance on image retrieval with much lower computational cost, outperforming the ones using feature maps for image representation.
卷积神经网络 (CNN) 中的激活隐藏单元，即特征图，主导着图像表示，这种表示是紧凑且具有判别力的。对于超大数据集，浮点格式的高维特征图不仅导致计算复杂度高，而且占用大量内存空间。为此，提出了一种新的图像表示方法，即聚合卷积核 (ACK)，其中一些捕获特定模式的卷积核被激活。直接以离散整数值提取卷积核的前-n 个索引数作为图像表示，从而重建卷积核与图像之间的关系。此外，还从有序集的角度定义了一种距离度量方法，用于计算图像表示之间的位置敏感相似度。在牛津建筑、巴黎和假日等数据集上进行的广泛实验表明，所提出的 ACK 在图像检索方面具有竞争力，计算成本低得多，优于使用特征图进行图像表示的方法。
