/Deep-Learning-Papers-Reading-List

Some Papers about Deep Learning especially Semantic Segmentation I have read

Deep-Learning-Papers-Reading-List

Table of Contents

Papers

Recognition

  • Handwritten Digit Recognition with a Back-Propagation Network(LeNet) [paper]
  • ImageNet Classification with Deep Convolutional Neural Networks(AlexNet) [paper]
  • Deep Sparse Rectifier Neural Networks(ReLU) paper
  • Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift(Batch-Norm) [paper]
  • Dropout: A Simple Way to Prevent Neural Networks from Overfitting(Dropout) [paper]
  • Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition(SPP) [paper]
  • Very Deep Convolutional Networks For Large-Scale Image Recognition(VGG) [paper]
  • Network In Network
  • Highway Networks
  • Going Deeper with Convolutions(GoogleNet)
  • Rethinking the Inception Architecture for Computer Vision(Inception v3) [paper]
  • PolyNet: A Pursuit of Structural Diversity in Very Deep Networks(PolyNet) [paper]
  • PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection(PVANet) [paper]
  • Deep Residual Learning for Image Recognition(ResNet)
  • Identity Mappings in Deep Residual Networks
  • Wide Residual Networks(Wide-ResNet)
  • Aggregated Residual Transformations for Deep Neural Networks
  • Xception: Deep Learning with Depthwise Separable Convolutions(Xception) [paper]
  • Densely Connected Convolutional Networks(DenseNet)
  • Squeeze-and-Excitation Networks(SENet) [paper]
  • MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications(MobileNet) [paper]
  • ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices(ShuffleNet) [paper]

Detection

  • Rich feature hierarchies for accurate object detection and semantic segmentation(RCNN)
  • Fast R-CNN
  • Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
  • DenseBox: Unifying Landmark Localization with End to End Object Detection(DenseBox) [paper]
  • You Only Look Once: Unified, Real-Time Object Detection(YOLO) [paper]
  • SSD: Single Shot MultiBox Detector(SSD) [paper]
  • DSSD : Deconvolutional Single Shot Detector(DSSD) [paper]
  • R-FCN: Object Detection via Region-based Fully Convolutional Networks(RFCN) [paper]
  • Feature Pyramid Networks for Object Detection(FPN) [paper]
  • Mask R-CNN [paper]
  • Focal Loss for Dense Object Detection(RetinaNet) [paper]
  • RON: Reverse Connection with Objectness Prior Networks for Object Detection(RON) [paper]
  • Deformable Convolutional Networks [paper]
  • Single-Shot Refinement Neural Network for Object Detection [paper]
  • Light-Head R-CNN: In Defense of Two-Stage Object Detector [paper]

Segmentation

semantic segmentation

  • Fully Convolutional Networks for Semantic Segmentation(FCN)
  • Learning Deconvolution Network for Semantic Segmentation(Deconv)
  • Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
  • Conditional Random Fields as Recurrent Neural Networks(CRFasRNN)
  • Semantic Image Segmentation via Deep Parsing Network(DPN)
  • Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation
  • Exploring Context with Deep Structured models for Semantic Segmentation
  • Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs(Deeplab v1)
  • DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution,and Fully Connected CRFs(Deeplab v2)
  • RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation(RefineNet)
  • Understanding Convolution for Semantic Segmentation(DUC)
  • Wider or Deeper: Revisiting the ResNet Model for Visual Recognition
  • Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascade
  • Loss Max-Pooling for Semantic Image Segmentation
  • Pyramid Scene Parsing Network(PSPNet)
  • Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network(GCN)
  • Rethinking Atrous Convolution for Semantic Image Segmentation(Deeplab v3)
  • Global-residual and Local-boundary Refinement Networks for Rectifying Scene Parsing Predictions
  • Stacked Deconvolutional Network for Semantic Segmentation(SDN)

instance segmentation

  • Instance-aware Semantic Segmentation via Multi-task Network Cascades(MNC) [paper]
  • Proposal-free Network for Instance-level Object Segmentation [paper]
  • Learning to Segment Object Candidates(DeepMask) [paper]
  • Learning to Refine Object Segments(SharpMask) [paper]
  • FastMask: Segment Multi-scale Object Candidates in One Shot(FastMask) [paper]
  • Instance-sensitive Fully Convolutional Networks(Instance-sensitive FCN) [paper]
  • Associative Embedding: End-to-End Learning for Joint Detection and Grouping [paper]
  • Fully Convolutional Instance-aware Semantic Segmentation(FCIS) [paper]
  • Mask R-CNN [paper]
  • Learning to Segment Every Thing [paper]
  • MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features [paper]

fast segmentation

  • SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation(SegNet)
  • ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation(ENet)
  • ICNet for Real-Time Semantic Segmentation(ICNet)

video segmentation

weakly segmentation

  • Weakly- and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation
  • BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
  • Constrained Convolutional Neural Networks for Weakly Supervised Segmentation
  • Augmented Feedback in Semantic Segmentation under Image Level Supervision
  • Webly Supervised Semantic Segmentation
  • Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach
  • Exploiting Saliency for Object Segmentation from Image Level Labels
  • Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation

saliency

  • A Model of Saliency-based Visual Attention for Rapid Scene Analysis [paper]
  • Saliency Detection: A Spectral Residual Approach
  • Large-Scale Optimization of Hierarchical Features for Saliency Prediction in Natural Images(eDN)
  • SALICON: Reducing the Semantic Gap in Saliency Prediction by Adapting Deep Neural Networks
  • SALICON: Saliency in Context Ming
  • Recurrent Attentional Networks for Saliency Detection
  • DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection
  • Deeply supervised salient object detection with short connections
  • What do different evaluation metrics tell us about saliency models?
  • Deep Level Sets for Salient Object Detection Ping
  • Non-Local Deep Features for Salient Object Detection
  • A Stagewise Refinement Model for Detecting Salient Objects in Images
  • Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection
  • Deep Contrast Learning for Salient Object Detection
  • Instance-Level Salient Object Segmentation
  • S4Net: Single Stage Salient-Instance Segmentation
  • Salient Object Detection: A Survey
  • Salient Object Detection: A Benchmark

Datasets

Segmentation

Saliency

Software and Skills

Framework

Skills