Choosing a set of CNNs for paper

There are so many CNNs out there and I am trying to do a comparison between some of them in my paper. Which networks should I include? Resnet, VGG, and Inception are obvious, but I would like three or four others. Which ones should I choose? There are so many variations out there like Xception, resnext, and ... that I am confused. Which of these networks are most used in the academic papers?

Topic inceptionresnetv2 convolutional-neural-network convolution deep-learning

Category Data Science


Following list of CNNs are most popular in research papers. And since, you are doing a comparative study, it would be interesting to choose from the below list.

  • Xception
  • VGG16
  • VGG19
  • ResNet,
  • ResNetV2
  • InceptionV3
  • InceptionResNetV2
  • MobileNet
  • MobileNetV2
  • DenseNet
  • NASNet

It largely depends what kind of paper you are writing — you haven't provided too much information in that regard. You could discuss a selection of models that have scored the highest on ImageNet. Most of these networks have historical significance, and brought a new aspect to the table.

About

Geeks Mental is a community that publishes articles and tutorials about Web, Android, Data Science, new techniques and Linux security.