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 …

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 …

Deep convolutional neural networks (CNN) have shown their promise as a universal
representation for recognition. However, global CNN activations lack geometric invariance …

Feature pooling layers (eg, max pooling) in convolutional neural networks (CNNs) serve the
dual purpose of providing increasingly abstract representations as well as yielding …

Pooling is a key mechanism in deep convolutional neural networks (CNNs) which helps to
achieve translation invariance. Numerous studies, both empirically and theoretically, show …

Recent results indicate that the generic descriptors extracted from the convolutional neural
networks are very powerful. This paper adds to the mounting evidence that this is indeed the …

MultiGrain is a network architecture producing compact vector representations that are
suited both for image classification and particular object retrieval. It builds on a standard …

Deep neural networks with alternating convolutional, max-pooling and decimation layers are
widely used in state of the art architectures for computer vision. Max-pooling purposefully …

Automatic analysis of scanned historical documents comprises a wide range of image
analysis tasks, which are often challenging for machine learning due to a lack of human …

In this paper we investigate whether Deep Convolutional Neural Networks (DCNNs), which
have obtained state of the art results on the ImageNet challenge, are able to perform equally …