Cross-Dimensional Weighting for Aggregated Deep Convolutional Features

We propose a simple and straightforward way of creating powerful image representations via cross-dimensional weighting and aggregation of deep convolutional neural network layer outputs. We first present a generalized framework that encompasses a broad family of approaches and includes cross-dimensional pooling and weighting steps. We then propose specific non-parametric schemes for both spatialand channel-wise weighting, that boost the effect of highly active spatial responses and at the same time regulate burstiness effects. We experiment on four public datasets for image search and unsupervised fine-grained classification and show that our approach consistently outperforms the current state-of-the-art by a large margin.