Get best of the week

新的神经网络架构

新的神经网络架构


网络


上一篇文章“ 神经网络。一切都去哪儿了？”


本文简要地讨论了一些神经网络体系结构，主要是在检测对象的任务上，以便找到（或至少试图找到）在这个快速发展的领域中的未来方向。


本文并不假装是全面的，并且对对角阅读文章有很好的理解。作者确信在他撰写本文时，还会出现更多新的体系结构。例如，请参见：https：//paperswithcode.com/area/computer-vision。



20年内的物体检测 -概述了20多年内用于检测物体的400多篇文章。


神经网络动物园是神经网络的动物园，其内容在不断变化。


一段有趣的视频，其中包含有关如何设计神经网络的建议：“ 如何设计神经网络 ”。



高效网


高效网


EfficientNet — , (, scaling) ( ) , . (compound scaling method), // . «Neural Architecture Search» (NAS, 1, 2, ) EfficientNets.


  • «EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks»
  • TensorFlow
  • 1, 2.1, 2.2, 3


EfficientDet


高效饮食


EfficientDet . . EfficientNet , BiFPN, «» / .


EfficientDet体系结构


— EfficientDet == EfficientNet + BiFPN + /


  • «EfficientDet: Scalable and Efficient Object Detection»
  • TensorFlow
  • PyTorch
  • 1


SpineNet


骨干网


SpineNet . Google Research , state-of-the-art (SOTA) .


. , ( ). () - « » (Convolutional Encoder-Decoder Neural Network). « » . , – (). (backbone model), , , . , « » , ().


SpineNet - ( ). (Neural Architecture Search, NAS). SpineNet (Average Precision, AP). .


通过置换ResNet构建规模置换网络


– ResNet (ResNet-50-FPN )


  • «SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization»
  • «SpineNet: »
  • SpineNet online demo


CenterNet


中心网


CenterNet CornerNet-Lite 2019 (c « »).


CenterNet , , . , , 3D-, , .. (image features) . , (heatmap). . . CenterNet 3D .


3 : , .


CenterNet图


– CenterNet


CornerNet CenterNet. CornerNet , : (bounding box). (anchor box), SSD YOLO, . « », .


CornerNet «corner pooling» . CenterNet «center pooling» .


CornerNet左上角池化层


– «corner pooling» . «max-pooling» «max-pooling». (feature maps) .


  • CenterNet «CenterNet: Keypoint Triplets for Object Detection» + 1 + 2
  • CornerNet-Lite «CornerNet-Lite: Efficient Keypoint Based Object Detection» +
  • CornerNet: «CornerNet: Detecting Objects as Paired Keypoints» + +


ThunderNet


雷网


ThunderNet . . , , ARM ( ) 24.1 fps (frames per second, ) MobileNet-SSD.


  • «ThunderNet: Towards Real-time Generic Object Detection»
  • GitHub

雷网架构


— ThunderNet



CSPNet


网络


CSPNet (Cross Stage Partial Network) Darknet, . , (residual neural networks, ResNet). , . , . CSPNet , . , CSPNet (feature pyramid network, FPN).


  • «CSPNet: A New Backbone that can Enhance Learning Capability of CNN»
  • 1, 2

功能金字塔网络，FPN


—



DenseNet


5层致密块，增长率为4


— DenseNet c 5 k = 4. .


具有三个密集块的DenseNet


— DenseNet


DenseNet (Densely Connected Convolutional Network) 2017 . ResNet (Deep Residual Network) , CNN . (dense) , . , , ResNet, («») , (, channel-wise concatenation) . DenseNet , . , DenseNet .


  • «Densely Connected Convolutional Networks»
  • Keras + CoLab
  • Torch ,


SAUNet


SAUNet (Shape Attentive U-Net) 2020 , .


SAUNet架构


— SAUNet : (texture stream); (gated shape stream). U-Net DenseNet-121 ( DenseNet), U-Net « » (dual attention decoder block).


SAUNet : U-Net, DenseNet, Gated-SCNN Squeeze-and-Excitation Networks.


  • «SAUNet: Shape Attentive U-Net for Interpretable Medical Image Segmentation»
  • PyTorch


DetNASNet


Detnasnet体系结构


— DetNASNet


, , , (object detection) (image classification) . DetNASNet Neural Architecture Search (NAS) , . , NAS, .. , . 44 GPU- COCO. , ResNet-101, FLOP-.


  • «DetNAS: Backbone Search for Object Detection»
  • PyTorch


SM-NAS


SM-NAS AP


— () (mAP) COCO.


SM-NAS Structural-to-Modular NAS (SM-NAS): ; .


  • .
  • «SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection»


AmoebaNet


AmoebaNet-A体系结构


— AmoebaNet-A. . «Normal Cell». «Reduction Cell».


AmoebaNet . AmoebaNet . AmoebaNet (search space), NASNet. TPU (Tensor Processing Units) .


  • «Regularized Evolution for Image Classifier Architecture Search»


Graph Neural Network


图神经网络


Graph Neural Network , — , — . , .. - . . : PyTorch Geometric PyTorch, Graph Nets TensorFlow, Deep Graph .


  • CoLab
  • by Siraj Raval
  • DGL (Deep Graph Library)


Growing Neural Cellular Automata


越来越多的神经细胞自动机


—


Growing Neural Cellular Automata , «» . (, ..). . «» 16 . «» , , JPEG (), MP3 (), MPEG () ZIP ().


, , () .


  • Distill
  • Colab notebook
  • by Yannic Kilcher
  • «»



Spiking neural network . . 1952 , . , . . , , , .


  • (ru, en)
  • PapersWithCode.com


DPM


DPM, Deformable Part Model detector, . ( CoLab) (HOG). - 2009 , , «Object Detection in 20 Years: A Survey», Integral Channel Features (ICF), .


«» , , , . , «Deformable Part Models are Convolutional Neural Networks» DPM .


  • «Deformable Part Models are Convolutional Neural Networks» + MatLab Caffe



  1. :


    • , AutoML, « », Neural Architecture Search (NAS NASNet);
    • (attention mechanism), ;
    • « » , (backbone) ;
    • , state-of-the-art (SOTA) .

  2. . , . , , . « » , — , .



PS我推荐视频博客ML Tokyo，作者在其中解释并在Keras上建立神经网络。他的CNN研讨会正是像我这样的新手“神经编码器”所需要的。


感谢您的关注！

More articles:


All Articles