• AlexNet

  • Referenced in 542 articles [sw38522]
  • AlexNet is a convolutional neural network that is 8 layers deep. You can load...
  • Keras

  • Referenced in 210 articles [sw15491]
  • total modularity, minimalism, and extensibility). supports both convolutional networks and recurrent networks, as well...
  • U-Net

  • Referenced in 132 articles [sw33176]
  • Convolutional networks for biomedical image segmentation. There is large consent that successful training of deep ... prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation...
  • SURF

  • Referenced in 183 articles [sw29761]
  • relying on integral images for image convolutions; by building on the strengths of the leading...
  • Faster R-CNN

  • Referenced in 71 articles [sw42495]
  • Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling ... region proposals. An RPN is a fully convolutional network that simultaneously predicts object bounds ... into a single network by sharing their convolutional features---using the recently popular terminology...
  • PDE-Net

  • Referenced in 91 articles [sw36963]
  • learn differential operators by learning convolution kernels (filters), and apply neural networks or other machine...
  • Sinc-Pack

  • Referenced in 76 articles [sw13600]
  • dimensional Sinc theory – 2. Sinc convolution-boundary integral equation methods for partial differential equations (PDEs...
  • DeepLab

  • Referenced in 39 articles [sw15303]
  • DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs ... have substantial practical merit. First, we highlight convolution with upsampled filters, or ’atrous convolution ... powerful tool in dense prediction tasks. Atrous convolution allows us to explicitly control the resolution ... which feature responses are computed within Deep Convolutional Neural Networks. It also allows...
  • DnCNN

  • Referenced in 50 articles [sw39678]
  • investigating the construction of feed-forward denoising convolutional neural networks (DnCNNs) to embrace the progress...
  • DeCAF

  • Referenced in 28 articles [sw17856]
  • DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition. We evaluate whether features extracted ... from the activation of a deep convolutional network trained in a fully supervised fashion ... visualize the semantic clustering of deep convolutional features with respect to a variety of such ... open-source implementation of these deep convolutional activation features, along with all associated network parameters...
  • Xception

  • Referenced in 23 articles [sw39068]
  • Xception: Deep Learning with Depthwise Separable Convolutions. We present an interpretation of Inception modules ... convolutional neural networks as being an intermediate step in-between regular convolution and the depthwise ... separable convolution operation (a depthwise convolution followed by a pointwise convolution). In this light ... depthwise separable convolution can be understood as an Inception module with a maximally large number...
  • XNOR-Net

  • Referenced in 23 articles [sw39593]
  • XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks. We propose two efficient approximations ... standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks. In Binary-Weight-Networks ... both the filters and the input to convolutional layers are binary. XNOR-Networks approximate convolutions ... binary operations. This results in 58x faster convolutional operations and 32x memory savings. XNOR-Nets...
  • SegNet

  • Referenced in 26 articles [sw27575]
  • SegNet: A deep convolutional encoder-decoder architecture for image segmentation. We present a novel ... practical deep fully convolutional neural network architecture for semantic pixel-wise segmentation termed SegNet. This ... network is topologically identical to the 13 convolutional layers in the VGG16 network. The role...
  • MobileNets

  • Referenced in 28 articles [sw39590]
  • MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. We present a class of efficient ... streamlined architecture that uses depth-wise separable convolutions to build light weight deep neural networks...
  • OverFeat

  • Referenced in 22 articles [sw17857]
  • OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks. We present an integrated framework ... using Convolutional Networks for classification, localization and detection. We show how a multiscale and sliding...
  • FaceNet

  • Referenced in 30 articles [sw21626]
  • feature vectors. Our method uses a deep convolutional network trained to directly optimize the embedding...
  • EfficientNet

  • Referenced in 21 articles [sw39587]
  • EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Convolutional Neural Networks (ConvNets) are commonly developed...
  • 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...
  • Inception-v4

  • Referenced in 29 articles [sw39592]
  • Residual Connections on Learning. Very deep convolutional networks have been central to the largest advances...
  • Glow

  • Referenced in 20 articles [sw34245]
  • Glow: Generative Flow with Invertible 1x1 Convolutions. Flow-based generative models (Dinh ... generative flow using an invertible 1x1 convolution. Using our method we demonstrate a significant improvement...