
AlexNet
 Referenced in 472 articles
[sw38522]
 AlexNet is a convolutional neural network that is 8 layers deep. You can load...

DnCNN
 Referenced in 45 articles
[sw39678]
 construction of feedforward denoising convolutional neural networks (DnCNNs) to embrace the progress in very...

DeepLab
 Referenced in 36 articles
[sw15303]
 feature responses are computed within Deep Convolutional Neural Networks. It also allows us to effectively ... multiple scales. ASPP probes an incoming convolutional feature layer with filters at multiple sampling rates...

Xception
 Referenced in 22 articles
[sw39068]
 interpretation of Inception modules in convolutional neural networks as being an intermediate step inbetween ... depthwise convolution followed by a pointwise convolution). In this light, a depthwise separable convolution ... propose a novel deep convolutional neural network architecture inspired by Inception, where Inception modules have ... been replaced with depthwise separable convolutions. We show that this architecture, dubbed Xception, slightly outperforms...

XNORNet
 Referenced in 21 articles
[sw39593]
 XNORNet: ImageNet Classification Using Binary Convolutional Neural Networks. We propose two efficient approximations ... convolutional neural networks: BinaryWeightNetworks and XNORNetworks. In BinaryWeightNetworks, the filters ... saving. In XNORNetworks, both the filters and the input to convolutional layers are binary...

SegNet
 Referenced in 27 articles
[sw27575]
 novel and practical deep fully convolutional neural network architecture for semantic pixelwise segmentation termed ... engine consists of an encoder network, a corresponding decoder network followed by a pixelwise ... encoder network is topologically identical to the 13 convolutional layers in the VGG16 network...

MatConvNet
 Referenced in 18 articles
[sw15651]
 MatConvNet – convolutional neural networks for MATLAB. MatConvNet is an open source implementation of Convolutional Neural ... MATLAB functions, providing routines for computing convolutions with filter banks, feature pooling, normalisation, and much...

MobileNets
 Referenced in 21 articles
[sw39590]
 MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. We present a class of efficient ... depthwise separable convolutions to build light weight deep neural networks. We introduce two simple...

PDENet
 Referenced in 63 articles
[sw36963]
 neural network designs in deep learning, we propose a new feedforward deep network, called ... differential operators by learning convolution kernels (filters), and apply neural networks or other machine learning...

EfficientNet
 Referenced in 11 articles
[sw39587]
 EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Convolutional Neural Networks (ConvNets) are commonly developed...

DoReFaNet
 Referenced in 11 articles
[sw36246]
 DoReFaNet: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients. We propose DoReFa ... method to train convolutional neural networks that have low bitwidth weights and activations using ... numbers before being propagated to convolutional layers. As convolutions during forward/backward passes can now operate ... accelerate training of low bitwidth neural network on these hardware. Our experiments on SVHN...

VoxNet
 Referenced in 10 articles
[sw36666]
 VoxNet: A 3D Convolutional Neural Network for realtime object recognition. Robust object recognition ... Grid representation with a supervised 3D Convolutional Neural Network (3D CNN). We evaluate our approach...

ShuffleNet
 Referenced in 12 articles
[sw39585]
 ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices. We introduce an extremely computation ... architecture utilizes two new operations, pointwise group convolution and channel shuffle, to greatly reduce computation...

VNet
 Referenced in 7 articles
[sw35860]
 Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. Convolutional Neural Networks (CNNs) have been ... segmentation based on a volumetric, fully convolutional, neural network. Our CNN is trained...

TopologyNet
 Referenced in 7 articles
[sw41013]
 TopologyNet: Topology based deep convolutional neural networks for biomolecular property predictions. Although deep learning approaches ... biomolecules. We further integrate ESPH and convolutional neural networks to construct a multichannel topological neural ... network (TopologyNet) for the predictions of proteinligand binding affinities and protein stability changes upon ... sets, we present a multitask topological convolutional neural network (MTTCNN). We demonstrate that...

SchNet
 Referenced in 7 articles
[sw40890]
 SchNet: a continuousfilter convolutional neural network for modeling quantum interactions. Deep learning ... exploration of chemical space. While convolutional neural networks have proven to be the first choice ... Thus, we propose to use continuousfilter convolutional layers to be able to model local...

PTE
 Referenced in 7 articles
[sw37756]
 Text Embedding through Largescale Heterogeneous Text Networks. Unsupervised text embedding methods, such as Skip ... sophisticated deep learning architectures such as convolutional neural networks, these methods usually yield inferior results ... represented as a largescale heterogeneous text network, which is then embedded into ... recent supervised approaches based on convolutional neural networks, predictive text embedding is comparable or more...

MgNet
 Referenced in 6 articles
[sw35862]
 unified framework of multigrid and convolutional neural network. We develop a unified model, known ... MgNet, that simultaneously recovers some convolutional neural networks (CNN) for image classification and multigrid ... unified model, the function of various convolution operations and pooling used...

Lasagne
 Referenced in 7 articles
[sw20936]
 neural networks in Theano. Its main features are: Supports feedforward networks such as Convolutional...

CNNRNN
 Referenced in 8 articles
[sw28401]
 Multilabel Image Classification. While deep convolutional neural networks (CNNs) have shown a great success...