A list to keep track of interesting papers I got the chance to read.
- CNN Structure
- [Object Recognition](#Object Recognition)
- Unsupervised/ Semi Supervised Learning
- Miscellaneous
- Network In Network
- Maxout Networks
- Dropout: A Simple Way to Prevent Neural Networks from Overtting
- Do Deep Nets Really Need to be Deep?
- ImageNet Classification with Deep Convolutional Neural Networks
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Going Deeper with Convolutions
- Batch Normalization Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
- Deep Residual Learning for Image Recognition
- Rethinking the Inception Architecture for Computer Vision
- Identity Mappings in Deep Residual Networks
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
- OverFeat: Integrated Recognition, Localization and Detectio
- Rich feature hierarchies for accurate object detection and semantic segmentation
- Learning to Segment Object Candidates
- Generative Adversarial Nets
- Tutorial on Variational Autoencoders
- Improved Techniques for Training GANs
- Semi-Supervised Learning with Generative Adversarial Networks
- Adversarial Feature Learning
- Joint Unsupervised Learning of Deep Representations and Image Clusters
- Context Encoders: Feature Learning by Inpainting
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Unsupervised Visual Representation Learning by Context Prediction
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- Building High-level Features Using Large Scale Unsupervised Learning
- One-Shot Generalization in Deep Generative Models
- Traffic Flow Prediction With Big Data: A Deep Learning Approach
- Dynamic Capacity Networks
- Net2Net: Accelerating Learning via Knowledge Transfer
- Deep Networks with Stochastic Depth
- Fully Convolutional Networks for Semantic Segmentation
- Do Deep Convolutional Nets Really Need to be Deep(Or Even Convolutional)?
- Do Deep Nets Really Need to be Deep?
- Perceptual Losses for Real-Time Style Transfer and Super-Resolution
- Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
- A Neural Algorithm of Artistic Style
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- Learning a Similarity Metric Discriminatively, with Application to Face Verification
- Optimal Brain Damage
- Perceptual Losses for Real-Time Style Transfer and Super-Resolution