Sort by: Year Popularity Relevance

Karol Zieba, Jake Zhao, Xin Zhang, Jiakai Zhang, Urs Muller, Mathew Monfort, Lawrence D. Jackel, Prasoon Goyal, Beat Flepp, Bernhard Firner, Daniel Dworakowski, Davide Del Testa, Mariusz Bojarski - 2016

We trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands. This end-to-end approach proved surprisingly powerful. With minimum training data from humans the system learns to drive in traffic on local roads with or without lane markings and on highways. It also operates in are...

Andrew Zisserman, Karen Simonyan - 2014

We investigate architectures of discriminatively trained deep Convolutional Networks (ConvNets) for action recognition in video. The challenge is to capture the complementary information on appearance from still frames and motion between frames. We also aim to generalise the best performing hand-crafted features within a data-driven learning fram...

Martin Riedmiller, Thomas Brox, Alexey Dosovitskiy, Jost Tobias Springenberg - 2014

Most modern convolutional neural networks (CNNs) used for object recognition are built using the same principles: Alternating convolution and max-pooling layers followed by a small number of fully connected layers. We re-evaluate the state of the art for object recognition from small images with convolutional networks, questioning the necessity o...

Yichen Wei, Han Hu, Guodong Zhang, Yi Li, Yuwen Xiong, Haozhi Qi, Jifeng Dai - 2017

Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in its building modules. In this work, we introduce two new modules to enhance the transformation modeling capacity of CNNs, namely, deformable convolution and deformable RoI pooling. Both are based on the idea of a...

Ran El Yaniv, Daniel Soudry, Itay Hubara - 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...

Yann N. Dauphin, Denis Yarats, David Grangier, Michael Auli, Jonas Gehring - 2017

The prevalent approach to sequence to sequence learning maps an input sequence to a variable length output sequence via recurrent neural networks. We introduce an architecture based entirely on convolutional neural networks. Compared to recurrent models, computations over all elements can be fully parallelized during training and optimization is ...

Max Welling, Thomas N. Kipf - 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...

Cong Yao, Xiang Bai, Baoguang Shi - 2015

Image-based sequence recognition has been a long-standing research topic in computer vision. In this paper, we investigate the problem of scene text recognition, which is among the most important and challenging tasks in image-based sequence recognition. A novel neural network architecture, which integrates feature extraction, sequence modeling a...

Vinay Shet, Sacha Arnoud, Julian Ibarz, Yaroslav Bulatov, Ian J. Goodfellow - 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...

Yann LeCun, Junbo Zhao, Xiang Zhang - 2015

This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification. We constructed several large-scale datasets to show that character-level convolutional networks could achieve state-of-the-art or competitive results. Comparisons are offered against traditional models such as bag ...