zd19901107/Deep-Learning-Papers-Reading-List

Some Papers about Deep Learning especially Semantic Segmentation I have read

Deep-Learning-Papers-Reading-List

Base

1. • Deep learning
2. • Handwritten Digit Recognition with a Back-Propagation Network (LeNet)
3. • ImageNet Classification with Deep Convolutional Neural Networks (AlexNet)
4. • Deep Sparse Rectifier Neural Networks (ReLU)
5. • Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (Batch-Norm)
6. • Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition (SPP)
7. • Network In Network (NIN)
8. • Highway Networks
9. • Deep Residual Learning for Image Recognition (ResNet)
10. • Identity Mappings in Deep Residual Networks
11. • Aggregated Residual Transformations for Deep Neural Networks (ResNeXt)
12. • Densely Connected Convolutional Networks (DenseNet)
13. • Wide Residual Networks (Wide-ResNet)
14. • Going Deeper with Convolutions (Inception)

Semantic Segmentation

Base

1. • Fully Convolutional Networks for Semantic Segmentation (FCN) [pdf]
2. • Learning Deconvolution Network for Semantic Segmentation (Deconvolution)
3. • Wider or Deeper: Revisiting the ResNet Model for Visual Recognition
4. • Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascade [pdf]
5. • Loss Max-Pooling for Semantic Image Segmentation [pdf]
6. • Understanding Convolution for Semantic Segmentation [pdf]
7. • Universal Adversarial Perturbations Against Semantic Image Segmentation [pdf]
8. • Rethinking Atrous Convolution for Semantic Image Segmentation(DeepLab v3) [pdf]

CRF/MRF

1. • Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials [pdf]
2. • Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs (DeepLab) [pdf]
3. • DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution,and Fully Connected CRFs (Deeplab v2) [pdf]
4. • Conditional Random Fields as Recurrent Neural Networks (CRFasRNN)[pdf]
5. • Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs (G-CRF) [pdf]
6. • Semantic Image Segmentation via Deep Parsing Network (DPN) [pdf]

Feature Ensembling

1. • Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation
2. • Exploring Context with Deep Structured models for Semantic Segmentation
3. • RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation (RefineNet)
4. • Pyramid Scene Parsing Network (PSPNet)
5. • Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network [pdf]

Fast Semantic Segmentation

1. • SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation (SegNet) [pdf]
2. • ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation (ENet) [pdf]
3. • ICNet for Real-Time Semantic Segmentation (ICNet)

Weakly-supervised

1. • Weakly- and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation
2. • BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation

Object Detection

1. • Rich feature hierarchies for accurate object detection and semantic segmentation (RCNN)
2. • Fast R-CNN (Fast RCNN)
3. • Faster R-CNN: Towards Real-Time Object (Faster RCNN) Detection with Region Proposal Networks
4. • Mask R-CNN (Mask RCNN)