• MatConvNet

  • Referenced in 15 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...
  • SegNet

  • Referenced in 17 articles [sw27575]
  • novel and practical deep fully convolutional neural network architecture for semantic pixel-wise segmentation termed ... engine consists of an encoder network, a corresponding decoder network followed by a pixel-wise ... encoder network is topologically identical to the 13 convolutional layers in the VGG16 network...
  • DeepLab

  • Referenced in 17 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...
  • PDE-Net

  • Referenced in 31 articles [sw36963]
  • neural network designs in deep learning, we propose a new feed-forward deep network, called ... differential operators by learning convolution kernels (filters), and apply neural networks or other machine learning...
  • V-Net

  • Referenced in 5 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...
  • PTE

  • Referenced in 6 articles [sw37756]
  • Text Embedding through Large-scale 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 large-scale heterogeneous text network, which is then embedded into ... recent supervised approaches based on convolutional neural networks, predictive text embedding is comparable or more...
  • VoxNet

  • Referenced in 6 articles [sw36666]
  • VoxNet: A 3D Convolutional Neural Network for real-time object recognition. Robust object recognition ... Grid representation with a supervised 3D Convolutional Neural Network (3D CNN). We evaluate our approach...
  • CNN-RNN

  • Referenced in 8 articles [sw28401]
  • Multi-label Image Classification. While deep convolutional neural networks (CNNs) have shown a great success...
  • Lasagne

  • Referenced in 6 articles [sw20936]
  • neural networks in Theano. Its main features are: Supports feed-forward networks such as Convolutional...
  • DoReFa-Net

  • Referenced in 4 articles [sw36246]
  • DoReFa-Net: 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...
  • SyncSpecCnn

  • Referenced in 5 articles [sw26163]
  • vertex functions on them by convolutional neural networks, we resort to spectral CNN method that ... graph laplacian eigenbases. Under this setting, our network, named SyncSpecCNN, strive to overcome ... introduce a spectral parameterization of dilated convolutional kernels and a spectral transformer network. Experimentally...
  • MgNet

  • Referenced in 3 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...
  • Conformer

  • Referenced in 3 articles [sw35794]
  • Speech Recognition. Recently Transformer and Convolution neural network (CNN) based models have shown promising results ... Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs). Transformer models are good at capturing ... worlds by studying how to combine convolution neural networks and transformers to model both local ... this regard, we propose the convolution-augmented transformer for speech recognition, named Conformer. Conformer significantly...
  • Keras

  • Referenced in 120 articles [sw15491]
  • Keras is a minimalist, highly modular neural networks library, written in Python and capable ... total modularity, minimalism, and extensibility). supports both convolutional networks and recurrent networks, as well...
  • JigsawNet

  • Referenced in 3 articles [sw25887]
  • JigsawNet: Shredded Image Reassembly using Convolutional Neural Network and Loop-based Composition. This paper proposes ... complicated puzzles. We build a deep convolutional neural network to detect the compatibility...
  • CayleyNets

  • Referenced in 4 articles [sw38090]
  • CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filters. The rise of graph-structured ... such as social networks, regulatory networks, citation graphs, and functional brain networks, in combination with ... paper, we introduce a new spectral domain convolutional architecture for deep learning on graphs...
  • SYNTHIA Dataset

  • Referenced in 4 articles [sw35060]
  • driving. Recent revolutionary results of deep convolutional neural networks (DCNNs) foreshadow the advent of reliable...
  • MeshCNN

  • Referenced in 3 articles [sw31207]
  • inhibits mesh analysis efforts using neural networks that combine convolution and pooling operations. In this ... shapes using MeshCNN, a convolutional neural network designed specifically for triangular meshes. Analogous to classic...
  • DeepTracker

  • Referenced in 2 articles [sw25889]
  • DeepTracker: Visualizing the Training Process of Convolutional Neural Networks. Deep convolutional neural networks (CNNs) have...
  • Pixel2Mesh

  • Referenced in 3 articles [sw31205]
  • Limited by the nature of deep neural network, previous methods usually represent a 3D shape ... mesh in a graph-based convolutional neural network and produces correct geometry by progressively deforming...