Papers-for-face-recognition

A. design neural networks

1. Going deeper with convolutions
2. Rethinking the Inception Architecture for Computer Vision
3. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
4. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
5. Deep Residual Learning for Image Recognition
6. Residual Networks are Exponential Ensembles of Relatively Shallow Networks
7. Speed/accuracy trade-offs for modern convolutional object detectors
8. Dropout: A simple way to prevent neural networks from overfitting

B. Autoencoders

1. Auto-Encoding Variational Bayes
2. Tutorial on Variational Autoencoders
3. Autoencoders, Unsupervised Learning, and Deep Architectures
4. A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines
5. Autoencoding beyond pixels using a learned similarity metric
6. DeepCoder: Semi-parametric Variational Autoencoders for Automatic Facial Action Coding
7. Extracting and Composing Robust Features with Denoising Autoencoders

C. Neural Networks compression

1. Distilling the Knowledge in a Neural Network
2. Model Distillation with Knowledge Transfer from Face Classification to Alignment and Verification
3. Fitnets: hints for thin deep nets
4. Born-Again Neural Network
5. Deep Model Compression: Distilling Knowledge from Noisy Teachers
6. Do Deep Convolutional nets really need to be deep and convolutional?
7. Compression of deep convolutional neural networks for fast and low power mobile appplications

D. Face recognition

1. OpenFace: A general-purpose facce recognition library with mobile applications
2. FaceNet: A Unified Embedding for Face Recognition and Clustering
3. Deep metric learning using triplet network

E. Super Resolution

1. Super-Resolution from a single image
2. Real-Time Single image and video super-resolution using an efficient sub-pixel convolutional neural network
3. image restoration using convolutional auto-encoders with symmetric skip connections

F. preprocessomg

1. One millisecond face alignment with an Ensemble of regression trees

G.