/paper-notes

A repository for easy note tracking and digestion.

Primary LanguagePython

Table of Contents generated with DocToc

Papers Organized By Task

Action Classification

Very Deep Convolutional Networks for Large-Scale Image Recognition

Object Classification

ImageNet Classification with Deep Convolutional Neural Networks
Visualizing and Understanding Convolutional Networks
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
Very Deep Convolutional Networks for Large-Scale Image Recognition
Going Deeper with Convolutions
Deeply Supervised Nets
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Rethinking the Inception Architecture for Computer Vision
Deep Residual Learning for Image Recognition
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Pulmonary nodule detection in CT images: false positive reduction using multi-view convolutional networks
ZNET - LUNG NODULE DETECTION
Multi-level Contextual 3D CNNs for False Positive Reduction in Pulmonary Nodule Detection
Accurate Pulmonary Nodule Detection in Computed Tomography Images Using Deep Convolutional Neural Networks
Squeeze-and-Excitation Networks
3D Deep Convolution Neural Network Application in Lung Nodule Detection on CT Images
Deep Learning Scaling is Predictable, Empirically
Deep Convolution Neural Networks for Pulmonary Nodule Detection in CT imaging
3DCNN for Lung Nodule Detection And False Positive Reduction
DeepLung: Deep 3D Dual Path Nets for Automated Pulmonary Nodule Detection and Classification
3D G-CNNs for Pulmonary Nodule Detection

Object Counting

Where are the Blobs: Counting by Localization with Point Supervision

Object Localization

OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
Very Deep Convolutional Networks for Large-Scale Image Recognition
Deep Residual Learning for Image Recognition

Object Detection

Rich feature hierarchies for accurate object detection and semantic segmentation
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
Going Deeper with Convolutions
Scalable, High-Quality Object Detection
Fast R-CNN
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
You Only Look Once: Unified, Real-Time Object Detection
SSD: Single Shot MultiBox Detector
Deep Residual Learning for Image Recognition
HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
R-FCN: Object Detection via Region-based Fully Convolutional Networks
ZNET - LUNG NODULE DETECTION
Speed/accuracy trade-offs for modern convolutional object detectors
Feature Pyramid Networks for Object Detection
YOLO9000: Better, Faster, Stronger
Deformable Convolutional Networks
Mask R-CNN
DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling
Soft-NMS -- Improving Object Detection With One Line of Code
Accurate Pulmonary Nodule Detection in Computed Tomography Images Using Deep Convolutional Neural Networks
Focal Loss for Dense Object Detection
Squeeze-and-Excitation Networks
3D Region Proposal U-Net with Dense and Residual Learning for Lung Nodule Detection
Single-Shot Refinement Neural Network for Object Detection
Non-local Neural Networks
3D Deep Convolution Neural Network Application in Lung Nodule Detection on CT Images
Deep Convolution Neural Networks for Pulmonary Nodule Detection in CT imaging
3DCNN for Lung Nodule Detection And False Positive Reduction
DeepLung: Deep 3D Dual Path Nets for Automated Pulmonary Nodule Detection and Classification
YOLOv3: An Incremental Improvement
S4ND: Single-Shot Single-Scale Lung Nodule Detection
3D Context Enhanced Region-based Convolutional Neural Network for End-to-End Lesion Detection
A Pulmonary Nodule Detection Model Based on Progressive Resolution and Hierarchical Saliency
Towards Single-phase Single-stage Detection of Pulmonary Nodules in Chest CT Imaging
CornerNet: Detecting Objects as Paired Keypoints

Scene Classification

Squeeze-and-Excitation Networks

Semantic Segmentation

Rich feature hierarchies for accurate object detection and semantic segmentation
Fully Convolutional Networks for Semantic Segmentation
Learning deconvolution network for semantic segmentation
U-Net: Convolutional Networks for Biomedical Image Segmentation
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
3D Deeply Supervised Network for Automatic Liver Segmentation from CT Volumes
CNN-based Segmentation of Medical Imaging
Deformable Convolutional Networks
Deeply-Supervised CNN for Prostate Segmentation
Attention U-Net: Learning Where to Look for the Pancreas
Learning To Segment Medical Images with Scribble-Supervision Alone

Instance Segmentation

Deep Residual Learning for Image Recognition
Associative Embedding: End-to-End Learning for Joint Detection and Grouping
Feature Pyramid Networks for Object Detection
Mask R-CNN
Non-local Neural Networks

Image Captioning

On the Automatic Generation of Medical Imaging Reports

Image Generation

Generative Adversarial Networks

Image Registration

Label-driven weakly-supervised learning for multimodal deformable image registration
An Unsupervised Learning Model for Deformable Medical Image Registration

Language Modeling

Deep Learning Scaling is Predictable, Empirically

Pose Estimation

Stacked Hourglass Networks for Human Pose Estimation
Associative Embedding: End-to-End Learning for Joint Detection and Grouping

Speech Recognition

Deep Learning Scaling is Predictable, Empirically

Cardiac Motion Scoring

Cardiac Motion Scoring with Segment- and Subject-level Non-Local Modeling

Papers Organized By Domain

Medical

U-Net: Convolutional Networks for Biomedical Image Segmentation
Pulmonary nodule detection in CT images: false positive reduction using multi-view convolutional networks
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
ZNET - LUNG NODULE DETECTION
3D Deeply Supervised Network for Automatic Liver Segmentation from CT Volumes
Multi-level Contextual 3D CNNs for False Positive Reduction in Pulmonary Nodule Detection
CNN-based Segmentation of Medical Imaging
Deeply-Supervised CNN for Prostate Segmentation
Accurate Pulmonary Nodule Detection in Computed Tomography Images Using Deep Convolutional Neural Networks
3D Region Proposal U-Net with Dense and Residual Learning for Lung Nodule Detection
Label-driven weakly-supervised learning for multimodal deformable image registration
On the Automatic Generation of Medical Imaging Reports
3D Deep Convolution Neural Network Application in Lung Nodule Detection on CT Images
Deep Convolution Neural Networks for Pulmonary Nodule Detection in CT imaging
3DCNN for Lung Nodule Detection And False Positive Reduction
DeepLung: Deep 3D Dual Path Nets for Automated Pulmonary Nodule Detection and Classification
An Unsupervised Learning Model for Deformable Medical Image Registration
Attention U-Net: Learning Where to Look for the Pancreas
3D G-CNNs for Pulmonary Nodule Detection
S4ND: Single-Shot Single-Scale Lung Nodule Detection
Cardiac Motion Scoring with Segment- and Subject-level Non-Local Modeling
3D Context Enhanced Region-based Convolutional Neural Network for End-to-End Lesion Detection
A Pulmonary Nodule Detection Model Based on Progressive Resolution and Hierarchical Saliency
Learning To Segment Medical Images with Scribble-Supervision Alone
Towards Single-phase Single-stage Detection of Pulmonary Nodules in Chest CT Imaging

Papers Organized By Topic

Deep Supervision

Going Deeper with Convolutions
Deeply Supervised Nets
Stacked Hourglass Networks for Human Pose Estimation
3D Deeply Supervised Network for Automatic Liver Segmentation from CT Volumes
CNN-based Segmentation of Medical Imaging
Deeply-Supervised CNN for Prostate Segmentation
Attention U-Net: Learning Where to Look for the Pancreas

Efficiency

You Only Look Once: Unified, Real-Time Object Detection
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
YOLO9000: Better, Faster, Stronger
YOLOv3: An Incremental Improvement

Generalization

Understanding deep learning requires rethinking generalization

Generative Adversarial Networks

Generative Adversarial Networks
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

Group Convolutions

3D G-CNNs for Pulmonary Nodule Detection

Loss Functions

Focal Loss for Dense Object Detection

Non Local Neural Networks

Non-local Neural Networks
Cardiac Motion Scoring with Segment- and Subject-level Non-Local Modeling

Post Processing

Soft-NMS -- Improving Object Detection With One Line of Code

Scalability

Deep Learning Scaling is Predictable, Empirically

Soft Attention

On the Automatic Generation of Medical Imaging Reports
Attention U-Net: Learning Where to Look for the Pancreas

Survey Papers

Speed/accuracy trade-offs for modern convolutional object detectors

Weak Supervision

Label-driven weakly-supervised learning for multimodal deformable image registration
Learning To Segment Medical Images with Scribble-Supervision Alone

Unsupervised Learning

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
An Unsupervised Learning Model for Deformable Medical Image Registration