About
This repository contains short summaries of some machine learning papers.
-
Added 2017/08/08:
-
Added 2017/06/11:
-
Added 2017/03/15:
-
Added 2017/03/14:
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- Faster R-CNN
- Fast R-CNN
- Rich feature hierarchies for accurate object detection and semantic segmentation (aka R-CNN)
- Ten Years of Pedestrian Detection, What Have We Learned?
- Instance Normalization: The Missing Ingredient for Fast Stylization
-
Added 2016/07/29:
-
Added 2016/07/01:
- Convolutional Pose Machines
- HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition
- Face Attribute Prediction Using Off-the-Shelf CNN Features
- CMS-RCNN: Contextual Multi-Scale Region-based CNN for Unconstrained Face Detection
- Conditional Image Generation with PixelCNN Decoders
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- Improved Techniques for Training GANs
- Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
-
Added 2016/06/06:
-
Added 2016/06/02:
- Resnet in Resnet: Generalizing Residual Architectures
- Rank Ordered Autoencoders
- Wide Residual Networks
- Identity Mappings in Deep Residual Networks
- Swapout: Learning an ensemble of deep architectures
- Multi-Scale Context Aggregation by Dilated Convolutions
- Texture Synthesis Through Convolutional Neural Networks and Spectrum Constraints
- Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks
-
Added 2016/05/15:
- Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artwork
- Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks
- Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
- Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
- Let there be Color
-
Added 2016/05/08:
-
Added 2016/05/03:
- Playing Atari with Deep Reinforcement Learning
- Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
- Noisy Activation Functions
- DenseCap: Fully Convolutional Localization Networks for Dense Captioning
-
Added 2016/04/01:
-
Added 2016/03/31:
- Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
- DRAW A Recurrent Neural Network for Image Generation
- Generating Images with Perceptual Similarity Metrics based on Deep Networks
- Generative Moment Matching Networks
- Pixel Recurrent Neural Networks
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
-
Added 2016/03/??:
- A Neural Algorithm for Artistic Style
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Deep Residual Learning for Image Recognition
- Fast and Accurate Deep Networks Learning By Exponential Linear Units (ELUs)
- Fractional Max-Pooling
- Generative Adversarial Networks
- Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
- Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks