论文标题
深度卷积特征的同时出现图像搜索
Co-occurrence of deep convolutional features for image search
论文作者
论文摘要
可以使用预先训练的卷积神经网络（CNN）的深度特征来解决图像搜索。来自CNN的最后一个卷积层的特征图编码描述性信息，可以从中获得歧视性的全局描述符。我们提出了来自深卷积特征的共发生的新表示，以从该最后一个卷积层中提取其他相关信息。将此同时映射与特征图相结合，我们获得了改进的图像表示。我们提出了两种不同的方法来获取共发生表示形式，这是基于激活的直接聚集的第一种方法，而第二种方法基于可训练的共发生表示形式。从我们的方法中得出的图像描述符在实验中证明的那样，从我们的方法学得出的图像描述提高了性能。
Image search can be tackled using deep features from pre-trained Convolutional Neural Networks (CNN). The feature map from the last convolutional layer of a CNN encodes descriptive information from which a discriminative global descriptor can be obtained. We propose a new representation of co-occurrences from deep convolutional features to extract additional relevant information from this last convolutional layer. Combining this co-occurrence map with the feature map, we achieve an improved image representation. We present two different methods to get the co-occurrence representation, the first one based on direct aggregation of activations, and the second one, based on a trainable co-occurrence representation. The image descriptors derived from our methodology improve the performance in very well-known image retrieval datasets as we prove in the experiments.
