Abstract

A number of recent studies have shown that a Deep Convolutional Neural Network (DCNN) pretrained on a large dataset can be adopted as a universal image descriptor, and that doing so leads to impressive performance at a range of image classifification tasks. Most of these studies, if not all, adopt activations of the fully-connected layer of a DCNN as the image or region representation and it is believed that convolutional layer activations are less discriminative. This paper, however, advocates that if used appropriately, convolutional layer activations constitute a powerful image representation. This is achieved by adopting a new technique proposed in this paper called crossconvolutional-layer pooling. More specififically, it extracts subarrays of feature maps of one convolutional layer as local features, and pools the extracted features with the guidance of the feature maps of the successive convolutional layer. Compared with existing methods that apply DCNNs in the similar local feature setting, the proposed method avoids the input image style mismatching issue which is usually encountered when applying fully connected layer activations to describe local regions. Also, the proposed method is easier to implement since it is codebook free and does not have any tuning parameters. By applying our method to four popular visual classifification tasks, it is demonstrated that the proposed method can achieve comparable or in some cases signifificantly better performance than existing fully-connected layer based image representations