/Research

CNN Research

This is Paper Collections.

1. CNN Architectures

  • AlexNet, Krizhevsky et al, 2014, Imagenet classification with deep convolutional neural networks, Link.

  • VGG16 and VGG19, Simonyan and Zisserman, 2014, Very Deep Convolutional Networks For Large-Scale Image Recognition, Link.

  • GoogLeNet, Szegedy et al, 2015, Going Deeper with Convolutions, Link.

  • ResNet, He et el, 2015, Deep Residual Learning for Image Recognition, Link.

(More Basics)

  • Network in Network, Lin et al, 2014, Network in Network, Link.

(Improving ResNet)

  • He et al, 2016, Identity Mappings In Deep Residual Networks, Link.
  • Zagoruyko et al, 2016, Wide Residual Networks, Link.
  • Xie et al, 2016, Aggregated Residual Transformations for Deep Neural Networks (ResNeXt) Link.
  • Huang et al, 2016, Deep Networks with Stochastic Depth, Link.

(Beyond ResNet)

  • Larsson et al, 2017, FractalNet: Ultra-Deep Neural Networks without Residuals, Link
  • Huang et al, 2017, Densley Connected Convolutional Networks, Link.
  • Iandola et al, 2017, SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size, Link.

...

2. Reviews

  • Yoshua Bengio, 2014, Representation Learning: A Review and New Perspectives, Link.
  • Yoshua Bengio, 2009, Learning Deep Architectures for AI, Link.

3. Visualizations

  • Zeiler and Fergus, 2013, Visualizing and Understanding Convolutional Networks, Link.
  • Yosinski et al, 2015, Understanding Neural Networks Through Deep Visualization, Link.
  • Springenberg et al, 2015, STRIVING FOR SIMPLICITY: THE ALL CONVOLUTIONAL NET, Link.
  • Simonyan, Vedeldi and Zisserman, 2014, Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps, Link.

Generative Models

1. Fully Visible Belief Nets

  • Aaron van den Oord et al, 2016, Conditional Image Generation with PixelCNN Decoders, Link.

2. Variational Autoencoders

  • Kingma and Welling, 2015, Auto-Encoding Variational Bayes, Link.

3. Generative Adversarial Network

  • Goodfellow et al, 2014, Generative Adversarial Nets, Link.
  • Radford et al, 2016, UNSUPERVISED REPRESENTATION LEARNING WITH DEEP CONVOLUTIONAL GENERATIVE ADVERSARIAL NETWORKS, Link.
  • Goodfellow, 2016, NIPS 2016 Tutorial: Generative Adversarial Networks, Link.

4. Adversarial Examples

  • Battista Biggio, 2013, Evasion attacks against machine learning at test time, Link.
  • Ian Goodfellow, EXPLAINING AND HARNESSING ADVERSARIAL EXAMPLES, Link.