/PaperWeekly

Papers for CNN, object detection, keypoint detection, semantic segmentation, medical image processing, transformers, etc.

PaperWeekly

Classical Image Features, Image Processing and Pattern Recognition

Paper Name Published time Link
Marr-1980 1980 link
Laws-Filters 1980 link
findContours 1985 link
cornerHarris 1988 link
GoodFeaturesToTrack 1993 IEEE
SIFT-1999 1999 iccv99
LBP 2002 link
HOG 2005 paper
SURF 2006 paper
FAST 2006 paper
DPM 2008 paper
BRIEF 2010 paper
VGG-Texture-Classification 2005 VGG
Deep Filter Banks 2015 CVPR
Live-Wire-1992 1992 link
Normalized-Cuts 1997 stanford
Bilateral-Filter 1998 link
Mattes-Mutual-Information 2001 harvard
Elastic Distortion 2003 cmu
IFT 2004 PAMI
Non-Local-Means 2005 paper
t-SNE visualization 2008 link
Histogram-Modification-Framework 2009 IEEE
gPb 2010 Berkeley
linemod 2012 link
Objectness 2012 PAMI
NumPy-Nature 2020 Nature

Attention, Transformer, Federated Learning, Self-Supervised Learning, One Class Classification

Paper Name Published time Link
Attention 2017 1706.03762
DETR 2020 2005.12872
ViT 2020 2010.11929
Vision-Transformers-Survey 2021 2101.01169
Rethinking-Generalization 2016 1611.03530
Data-HFC-CNN 2019 1905.13545
Contrastive-Loss-Function 2006 LeCun
Nature-Deep-Learning 2015 Nature
Federated-Averaging 2016 1602.05629
Deep-Learning-Computer-Architecture-Chip-Design 2019 1911.05289
DL-Critical-Appraisal 2018 1801.00631
DL-vs-Traditional-CV 2019 1910.13796
Federated-Machine-Learning 2019 1902.04885
Federated-Learning-At-Scale 2019 1902.01046
ML-Stuck-in-a-Rut 2019 HotOS-2019
Self-supervised-representation-learning-revisited 2019 1901.09005
Momentum-Contrast 2019 1911.05722
SimCLR 2020 2002.05079
Deep OCC 2018 1801.05365v2
OC-CNN 2019 1901.08688v1

Classification models and algorithms

Model name Published time Link
AlexNet 2012 nips link
Visualization 2013 1311.2901
Inception V1 i.e. GoogLeNet 2014 1409.4842v1
Inception V2 2015 1502.03167v3
Inception V3 2015 1512.00567v3
Inception V4 2016 1602.07261v2
Xception 2016 1610.02357v3
VGG 2014 1409.1556
Spatial-Transformer-Networks 2015 1506.02025
ResNet V1 2015 1512.03385
ResNet V2 2016 1603.05027
ResNeXt 2016 1611.05431
DenseNet 2016 1608.06993
ShuffleNetV1 2017 1707.01083
ShuffleNetV2 2018 1807.11164
MobileNet 2017 1704.04861
MobileNetV2 2018 1801.04381v3
SENet 2017 1709.01507
MnasNet 2018 1807.11626
OctConv 2019 1904.0509
MobileNetV3 2019 1905.02244
EfficientNet 2019 1905.11946
ResNeSt 2020 2004.08955
Non-local NN 2017 1711.07971
ResNet-RS 2021 2103.07579
RandAugment 2019 1909.13719
Deformable-CNN-v1 2017 1703.06211
Deformable-CNN-v2 2018 1811.11168

Object Detetion models and algorithms

Model name Published time Link
SelectiveSearch 2012 personal link
R-CNN 2014 1311.2524v5
Fast R-CNN 2015 1504.08083v2
Faster R-CNN 2016 1506.01497
Mask R-CNN 2018 1703.06870v3
SSD 2016 1512.02325v5
Speed/accuracy trade-offs 2016 1611.10012v3
YOLOv1 2015 1506.02640
YOLO9000 2016 1612.08242
YOLOv3 2018 1804.02767
YOLOv4 2020 2004.10934
R-FCN 2016 1605.06409
Focal Loss 2017 1708.02002
Feature Pyramid Network 2017 1612.03144
CornerNet 2018 1808.01244
CenterNet 2019 1904.07850
NAS-FPN 2019 1904.07392
EfficientDet 2019 1911.09070

Semantic Segmentation

Model name Published time Link
FCN 2015 1411.4038
DeepLabV1 2015 1412.7062
DeepLabV2 2016 1606.00915
DeepLabV3 2017 1706.05587
DeepLabV3+ 2018 1802.02611
Dense-Prediction-Architecture-Search 2018 1809.04184
Auto-DeepLab 2019 1901.02985
Boundary-Loss 2018 1812.07032
U-Net-Medical 2015 1505.04597
V-Net 2016 1606.04797
Clinically-Applicable-DL-OAR-Delineation 2019 Nature
nnU-Net 2019 1904.08128
Fast-SCNN 2019 1902.04502

GAN

Model name Published time Link
GAN 2014 1406.2661
cGAN 2014 1411.1784
DCGAN 2015 1511.06434
Improved-Techniques-for-Training-GANs 2016 1606.03498
pix2pix 2016 1611.07004
CycleGAN 2017 1703.10593

Keypoint detection

Paper Published time Link
Convolutional Pose Machines 2016 1602.00134
Part Affinity Fields 2016 1611.08050
Hand keypoint detection 2017 1704.07809
OpenPose 2018 1812.08008

Face Detection & Alignment & Recognition

Paper Published time Link
FaceNet 2015 1503.03832
MTCNN 2016 1604.02878v1
SSH 2017 1708.03979
ArcFace 2018 1801.07698
MobileFaceNet 2018 1804.07573
RetinaFace 2019 1905.00641

Inference Framework and Pruning, Quantization, Compression, AutoML

Name Published time Link
CNN-FFT 2014 1312.5851v5
FFT-DL-Deploy 2017 1712.04910
Caffe 2014 1408.5093
Knowledge-Distilling 2015 1503.02531
Learning-weights-and-connections 2015 1506.02626
Deep-Compression 2015 1510.00149
Pruning-Filters 2016 1608.08710
TVM 2018 1802.04799
Integer-Arithmetic-Inference 2018 1712.05877
Quantization 2018 1806.08342
Auto-Keras 2018 1806.10282

Image Registration & Optical Flow

Name Published time Link
FlowNet 2015 1504.06852
FlowNetV2 2016 1612.01925
Geometric-Mapping-CNN 2017 1703.05593
CNN-3D-2D-Registration 2016 1507.07505
MV-3D-2D-CNN-Registration 2018 1811.11816
VoxelMorph 2018 1809.05231
X-ray-CT-Registration 2019 MICCAI2019
Weakly-Supervised-CNN-Multimodal-Registration 2018 1807.03361
POINT2 2019 1903.03896

Medical Imaging and Medical Image Processing

Name Published time Link
DRR-Siddon-1985 1985 aapm
DRR-Jacob-1998 1998 semanticscholar
DRR-GPU-deGreef-2009 2009 aapm
MRI-sCT-Generation-Review 2017 Radioation Oncology
Survey-DL-Medical 2017 1702.05747
CycleGAN-UNIT-comparison 2018 1806.07777v1
DL-Registration-Survey 2019 1903.02026
Models Genesis 2019 1908.06912
Radiomics-ML-DL 2020 aapm
Intrafractional-motion-management 2020 pubmed
UltraSound-Toolbox 2017 IEEE
ALTIS 2019 pubmed
CBCT-Scatter-Compensation 2011 aapm
CBCT-Scatter-Estimation 2011 aapm
CT-Survey 2013 springer
CT-Reconstruction-Evolution 2019 springer
CT-RED-CNN 2017 IEEE

OCR & Action Recognition & Spatial-temporal CNN & Image Super-Resolution & Crowd counting

Model Published time Link
I3D 2017 1705.07750
FCN-rLSTM 2017 1707.09476
Bi-ConvLSTM 2017 1707.07890
EDSR 2017 1707.02921v1
Deep image prior 2018 github.io
MCNN 2016 CVPR2016
MSCNN 2017 1702.02359
OCR review 2018 1811.04256

Datasets

Datasets name Published time Link
MS COCO 2014 1405.0312
MPII 2014 CVPR'14
CrowdHuman 2018 1805.00123
fddb 2010 fddb
WIDER-FACE 2015 1511.06523
MS-Celeb-1M 2016 1607.08221
CV-HAZOP 2017 IJCV2017
DeepLesion 2018 SPIE
RIL-Contour 2019 Mayo
Data-Cascades 2021 google

3D Point Cloud & Other

Paper time link
PCL-Library 2011 PCL
Open3D 2018 1801.09847
HED 2015 1504.06375
FireNet 2018 personal link
Contour-to-DICOM-RT-Structure-Set 2009 link
stochasticity 2000 link

Books & links

  1. 深度学习入门:基于Python的理论与实现
  2. 解析卷积神经网络—深度学习实践手册
  3. DMD orign
  4. TI-DLP
  5. Camera-Calibration-Matlab
  6. SimpleITK