Research Notes:: Deep Learning

---

Part 1 of the Deep Learning series

Next articles

• Neural Networks for Computer Vision
• Style Transfer, Part 1
• Style Transfer, Part 2
• Neural Network Architectures
• Object Detection and Image Segmentation
• Object Detection and Image Segmentation, Part 2

Contents:

---

Very minimal notes on some papers or articles that I recently read. Mainly for logging purposes.

Image Recognition and Convnet Architectures

• Image Recognition
  • Very Deep Convolutional Networks For Large-Scale Image Recognition
  • Going Deeper with Convolutions
  • Deep Residual Learning for Image Recognition
  • Rethinking the Inception Architecture for Computer Vision
  • Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
  • Xception: Deep Learning with Depthwise Separable Convolutions
• Deep Visualization
  • Visualizing and Understanding Convolutional Networks
  • Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks
  • How transferable are features in deep neural networks?

Style Transfer, Part 1

• Style Transfer
  • A Neural Style Algorithm of Artistic Style
  • Improving the Neural Algorithm of Artistic Style
  • Preserving Color in Neural Artistic Style Transfer

Style Transfer, Part 2

• Style Transfer
  • Artistic style transfer for videos
  • Instance Normalization: The Missing Ingredient for Fast Stylization
  • Perceptual Losses for Real-Time Style Transfer and Super Resolution
  • Stylizing Face Images via Multiple Exemplars

Neural Network Architectures

• Deep Learning Architectures
  • Self-Normalizing Neural Networks
  • Understanding deep learning requires rethinking generalization

Object Detection and Image Segmentation, Part 1

• Image Segmentation
  • Image segmentation review
  • Rich feature hierarchies for accurate object detection and semantic segmentation
  • Fast R-CNN
  • Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
  • Mask R-CNN
  • A Review of Deep Learning Techniques Applied to Semantic Segmentation
  • DeepLab : Semantic Image Segmentation with Deep Convolution Nets, Atrous Convolution, and Fully Connected CRFs
  • U-Net: Convolution Networks for Biomedical Image Segmentation
  • Fully Convolutional Networks for Semantic Segmentation
  • From Image-level to Pixel-level Labeling with Convolutional Networks

Object Detection and Image Segmentation, Part 2

• Image Segmentation
  • SSD: Single Shot MultiBox Detector
  • OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks