Sort by: Year Popularity Relevance

Semi-Supervised Classification with Graph Convolutional Networks

,  - 2016

We present a scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs. We motivate the choice of our convolutional architecture via a localized first-order approximation of spectral graph convolutions. Our model scales linearly i...


LipNet: End-to-End Sentence-level Lipreading

, , ,  - 2016

Lipreading is the task of decoding text from the movement of a speaker's mouth. Traditional approaches separated the problem into two stages: designing or learning visual features, and prediction. More recent deep lipreading approaches are end-to-end trainable (Wand et al., 2016; Chung & Zisserman, 2016a). However, existing work on models trained...


Accurate Image Super-Resolution Using Very Deep Convolutional Networks

, ,  - 2015

We present a highly accurate single-image super-resolution (SR) method. Our method uses a very deep convolutional network inspired by VGG-net used for ImageNet classification \cite{simonyan2015very}. We find increasing our network depth shows a significant improvement in accuracy. Our final model uses 20 weight layers. By cascading small filters ...


Semi-Supervised Learning with Deep Generative Models

, , ,  - 2014

The ever-increasing size of modern data sets combined with the difficulty of obtaining label information has made semi-supervised learning one of the problems of significant practical importance in modern data analysis. We revisit the approach to semi-supervised learning with generative models and develop new models that allow for effective gener...


Long-term Recurrent Convolutional Networks for Visual Recognition and Description

, , , , , ,  - 2014

Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or "temporally deep", are effective for tasks involving sequences, visual and otherwise. We develop a novel recurrent convolutional architecture suitable for large-scale visual learning which is end...


Dual Path Networks

, , , , ,  - 2017

In this work, we present a simple, highly efficient and modularized Dual Path Network (DPN) for image classification which presents a new topology of connection paths internally. By revealing the equivalence of the state-of-the-art Residual Network (ResNet) and Densely Convolutional Network (DenseNet) within the HORNN framework, we find that ResN...


Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks

, , , ,  - 2013

Recognizing arbitrary multi-character text in unconstrained natural photographs is a hard problem. In this paper, we address an equally hard sub-problem in this domain viz. recognizing arbitrary multi-digit numbers from Street View imagery. Traditional approaches to solve this problem typically separate out the localization, segmentation, and rec...


Deep Learning applied to NLP

,  - 2017

Convolutional Neural Network (CNNs) are typically associated with Computer Vision. CNNs are responsible for major breakthroughs in Image Classification and are the core of most Computer Vision systems today. More recently CNNs have been applied to problems in Natural Language Processing and gotten some interesting results. In this paper, we will ...


Binarized Neural Networks

, ,  - 2016

We introduce a method to train Binarized Neural Networks (BNNs) - neural networks with binary weights and activations at run-time and when computing the parameters' gradient at train-time. We conduct two sets of experiments, each based on a different framework, namely Torch7 and Theano, where we train BNNs on MNIST, CIFAR-10 and SVHN, and achieve...


Random Erasing Data Augmentation

, , , ,  - 2017

In this paper, we introduce Random Erasing, a simple yet effective data augmentation techniques for training the convolutional neural network (CNN). In training phase, Random Erasing randomly selects a rectangle region in an image, and erases its pixels with random values. In this process, training images with various levels of occlusion are gene...