Full end-to-end text recognition in natural images is a challenging problem that has received
much attention recently. Traditional systems in this area have relied on elaborate models …

We describe PhotoOCR, a system for text extraction from images. Our particular focus is
reliable text extraction from smartphone imagery, with the goal of text recognition as a user …

We classify digits of real-world house numbers using convolutional neural networks
(ConvNets). Con-vNets are hierarchical feature learning neural networks whose structure is …

The overhead of saving checkpoints to stable storage is the dominant performance cost in
checkpointing systems. In this paper, we present a complete study of compressed di …

Transfer learning is a deep-learning technique that ameliorates the problem of learning
when human-annotated labels are expensive and limited. In place of such labels, it uses …

Convolutional Neural Networks (CNN) are on the forefront of accurate character recognition.
This paper explores CNNs at their maximum capacity by implementing the use of large …

The need for consistent treatment of uncertainty has recently triggered increased interest in
probabilistic deep learning methods. However, most current approaches have severe …

Recognition across domains has recently become an active topic in the research
community. However, it has been largely overlooked in the problem of recognition in new …

The aim of this work is to address catastrophic forgetting in class-incremental learning. To
this end, we propose deep networks that comprise blocks of units that compete locally to win …

Data interpolation is typically used to explore and understand the latent representation
learnt by a deep network. Naive linear interpolation may induce mismatch between the …