• Faster R-CNN

  • Referenced in 71 articles [sw42495]
  • Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. State ... locations. Advances like SPPnet and Fast R-CNN have reduced the running time of these ... proposals, which are used by Fast R-CNN for detection. We further merge ... Fast R-CNN into a single network by sharing their convolutional features---using the recently...
  • CNN

  • Referenced in 57 articles [sw33973]
  • CNN Technology: Template and software library...
  • DnCNN

  • Referenced in 50 articles [sw39678]
  • Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising. Discriminative model learning for image...
  • SSD

  • Referenced in 34 articles [sw26652]
  • comparable state of the art Faster R-CNN model...
  • YOLO

  • Referenced in 20 articles [sw28515]
  • single network evaluation unlike systems like R-CNN which require thousands for a single image ... fast, more than 1000x faster than R-CNN and 100x faster than Fast ... CNN. See our paper for more details on the full system...
  • Grad-CAM

  • Referenced in 23 articles [sw35098]
  • decisions from a large class of CNN-based models, making them more transparent. Our approach ... applicable to a wide variety of CNN model-families: (1) CNNs with fully-connected layers...
  • MatConvNet

  • Referenced in 18 articles [sw15651]
  • MATLAB code, allowing fast prototyping of new CNN architectures. At the same time, it supports...
  • ShuffleNet

  • Referenced in 16 articles [sw39585]
  • Devices. We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially...
  • MODA

  • Referenced in 15 articles [sw02572]
  • compared with known paradigms of ANN and CNN. Results of simulations are also reported...
  • MgNet

  • Referenced in 7 articles [sw35862]
  • that simultaneously recovers some convolutional neural networks (CNN) for image classification and multigrid (MG) methods ... have observed and uncovered between the CNN and MG methodologies. For example, pooling operation ... feature extraction in CNN correspond directly to restriction operation and iterative smoothers in MG, respectively ... dual to each other) is introduced in CNN. With such connections and new concept...
  • CNN-RNN

  • Referenced in 8 articles [sw28401]
  • CNN-RNN: A Unified Framework for Multi-label Image Classification. While deep convolutional neural networks ... this problem. Combined with CNNs, the proposed CNN-RNN framework learns a joint image-label...
  • VoxNet

  • Referenced in 12 articles [sw36666]
  • supervised 3D Convolutional Neural Network (3D CNN). We evaluate our approach on publicly available benchmarks...
  • PWC-Net

  • Referenced in 5 articles [sw38830]
  • Volume. We present a compact but effective CNN model for optical flow, called ... rent optical flow estimate to warp the CNN features of the second image. It then ... cost volume, which is processed by a CNN to estimate the optical flow...
  • AOD-Net

  • Referenced in 4 articles [sw42512]
  • model built with a convolutional neural network (CNN), called All-in-One Dehazing Network ... clean image through a light-weight CNN. Such a novel end-to-end design makes ... into other deep models, e.g., Faster R-CNN, for improving high-level tasks on hazy ... when concatenating AOD-Net with Faster R-CNN, we witness a large improvement...
  • SyncSpecCnn

  • Referenced in 5 articles [sw26163]
  • SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation. In this paper, we study the problem ... convolutional neural networks, we resort to spectral CNN method that enables weight sharing by parameterizing...
  • DiscretizationNet

  • Referenced in 7 articles [sw42183]
  • solver, DiscretizationNet, employs a generative CNN-based encoder-decoder model with PDE variables as both...
  • CBAM

  • Referenced in 7 articles [sw42531]
  • module, it can be integrated into any CNN architectures seamlessly with negligible overheads...
  • Detectron

  • Referenced in 6 articles [sw30742]
  • object detection algorithms, including Mask R-CNN. It is written in Python and powered...
  • V-Net

  • Referenced in 6 articles [sw35860]
  • volumetric, fully convolutional, neural network. Our CNN is trained end-to-end on MRI volumes...
  • ProxylessNAS

  • Referenced in 6 articles [sw42534]
  • latency) and provide insights for efficient CNN architecture design...