Although there have been encouraging breakthroughs in supervised learning since the
renaissance of deep learning, the recognition of large-scale object classes remains a …

Global pooling layers are an essential part of Convolutional Neural Networks (CNN). They
are used to aggregate activations of spatial locations to produce a fixed-size vector in …

In content-based image retrieval (CBIR), one of the most challenging and ambiguous tasks
is to correctly understand the human query intention and measure its semantic relevance …

The encoding of local features is an essential part for writer identification and writer retrieval.
While CNN activations have already been used as local features in related works, the …

Most recent CNN architectures use average pooling as a final feature encoding step. In the
field of fine-grained recognition, however, recent global representations like bilinear pooling …

We present a generic unsupervised method to increase the discriminative power of image
vectors obtained from a broad family of deep neural networks for object retrieval. This goal is …

Aggregated second-order features extracted from deep convolutional networks have been
shown to be effective for texture generation, fine-grained recognition, material classification …

Image retrieval based on deep convolutional features has demonstrated state-of-the-art
performance in popular benchmarks. In this paper, we present a unified solution to address …

With the rapid development of deep learning methods, researchers have gradually shifted
the research focus from hand-crafted features to deep features in the field of the content …

A common architectural choice for deep metric learning is a convolutional neural network
followed by global average pooling (GAP). Albeit simple, GAP is a highly effective way to …