| 1 |
Gradient-Based Learning Applied to Document Recognition |
LeNet5 |
🔗 |
🔗 |
| 2 |
ImageNet Classification with Deep Convolutional Neural Networks |
AlexNet |
🔗 |
🔗 |
| 3 |
VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION |
VGGNet |
🔗 |
🔗 |
| 4 |
Visualizing and Understanding Convolutional Networks |
ZFNet，卷积网络可视化，反卷积网络 |
🔗 |
🔗 |
| 5 |
Going deeper with convolutions |
GoogLeNet，Inception-v1 |
🔗 |
🔗 |
| 6 |
Rich feature hierarchies for accurate object detection and semantic segmentation |
R-CNN |
🔗 |
🔗 |
| 7 |
Generative Adversarial Nets |
GAN |
🔗 |
🔗 |
| 8 |
Selective Search for Object Recognition |
Selective Search算法 |
🔗 |
🔗 |
| 9 |
Efficient Graph-Based Image Segmentation |
NULL |
🔗 |
🔗 |
| 10 |
Batch Normalization：Accelerating Deep Network Training by Reducing Internal Covariate Shift |
Batch Normalization，BN-Inception |
🔗 |
🔗 |
| 11 |
Interactive Graph Cuts for Optimal Boundary & Region Segmentation of Objects in N-D Images |
GraphCut算法 |
🔗 |
🔗 |
| 12 |
“GrabCut” — Interactive Foreground Extraction using Iterated Graph Cuts |
GrabCut算法 |
🔗 |
🔗 |
| 13 |
Topological Structural Analysis of Digitized Binary Images by Border Following |
Border Following，cv::findContours原理 |
🔗 |
🔗 |
| 14 |
Rethinking the Inception Architecture for Computer Vision |
Inception-v2，Inception-v3 |
🔗 |
🔗 |
| 15 |
U-Net: Convolutional Networks for Biomedical Image Segmentation |
U-Net |
🔗 |
🔗 |
| 16 |
Fully Convolutional Networks for Semantic Segmentation |
FCN，shift-and-stitch，backwards convolution，deconvolution |
🔗 |
🔗 |
| 17 |
Deep Residual Learning for Image Recognition |
ResNet |
🔗 |
🔗 |
| 18 |
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning |
Inception-v4，Inception-ResNet |
🔗 |
🔗 |
| 19 |
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition |
SPP-net |
🔗 |
🔗 |
| 20 |
Best Practices for Convolutional Neural Networks Applied to Visual Document Analysis |
Elastic Distortions |
🔗 |
🔗 |
| 21 |
Fast R-CNN |
Fast R-CNN |
🔗 |
🔗 |
| 22 |
Layer Normalization |
Layer Normalization |
🔗 |
🔗 |
| 23 |
Attention Is All You Need |
Transformer，Multi-Head Attention |
🔗 |
🔗 |
| 24 |
Faster R-CNN：Towards Real-Time Object Detection with Region Proposal Networks |
Faster R-CNN，Region Proposal Networks（RPN） |
🔗 |
🔗 |
| 25 |
FAST AND ACCURATE DEEP NETWORK LEARNING BY EXPONENTIAL LINEAR UNITS (ELUS) |
exponential linear unit（ELU）激活函数，Shifted ReLU（SReLU）激活函数 |
🔗 |
🔗 |
| 26 |
GAUSSIAN ERROR LINEAR UNITS (GELUS) |
Gaussian Error Linear Unit（GELU）激活函数，Sigmoid Linear Unit（SiLU）激活函数 |
🔗 |
🔗 |
| 27 |
You Only Look Once： Unified, Real-Time Object Detection |
YOLOv1 |
🔗 |
🔗 |
| 28 |
YOLO9000：Better, Faster, Stronger |
YOLOv2，YOLO9000 |
🔗 |
🔗 |
| 29 |
YOLOv3：An Incremental Improvement |
YOLOv3，Darknet-53 |
🔗 |
🔗 |
| 30 |
AN IMAGE IS WORTH 16X16 WORDS：TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE |
Vision Transformer（ViT） |
🔗 |
🔗 |
| 31 |
Distribution-Aware Coordinate Representation for Human Pose Estimation |
DARK |
🔗 |
🔗 |
| 32 |
ViTPose：Simple Vision Transformer Baselines for Human Pose Estimation |
ViTPose，Human Pose Estimation |
🔗 |
🔗 |
| 33 |
Swin Transformer：Hierarchical Vision Transformer using Shifted Windows |
Swin Transformer |
🔗 |
🔗 |
| 34 |
Deep High-Resolution Representation Learning for Visual Recognition |
HRNet |
🔗 |
🔗 |
| 35 |
FlowNet：Learning Optical Flow with Convolutional Networks |
FlowNet |
🔗 |
🔗 |
| 36 |
FlowNet 2.0：Evolution of Optical Flow Estimation with Deep Networks |
FlowNet2 |
🔗 |
🔗 |
| 37 |
3D Convolutional Neural Networks for Human Action Recognition |
3D卷积 |
🔗 |
🔗 |
| 38 |
3D U-Net：Learning Dense Volumetric Segmentation from Sparse Annotation |
3D U-Net |
🔗 |
🔗 |
| 39 |
V-Net：Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation |
V-Net，dice loss |
🔗 |
🔗 |
| 40 |
SURF：Speeded Up Robust Features |
SURF，U-SURF |
🔗 |
🔗 |
| 41 |
nnU-Net：Self-adapting Framework for U-Net-Based Medical Image Segmentation |
nnU-Net |
🔗 |
🔗 |
| 42 |
Histograms of Oriented Gradients for Human Detection |
HOG |
🔗 |
🔗 |
| 43 |
PERCEIVER IO：A GENERAL ARCHITECTURE FOR STRUCTURED INPUTS & OUTPUTS |
Perceiver IO |
🔗 |
🔗 |
| 44 |
Densely Connected Convolutional Networks |
DenseNet |
🔗 |
🔗 |
| 45 |
SimCC：a Simple Coordinate Classification Perspective for Human Pose Estimation |
SimCC |
🔗 |
🔗 |
| 46 |
Network In Network |
NIN |
🔗 |
🔗 |
| 47 |
Aggregated Residual Transformations for Deep Neural Networks |
ResNeXt |
🔗 |
🔗 |
| 48 |
CSPNET：A NEW BACKBONE THAT CAN ENHANCE LEARNING CAPABILITY OF CNN |
CSPNet |
🔗 |
🔗 |
| 49 |
Feature Pyramid Networks for Object Detection |
FPN |
🔗 |
🔗 |
| 50 |
Mask R-CNN |
Mask R-CNN |
🔗 |
🔗 |
| 51 |
Path Aggregation Network for Instance Segmentation |
PANet |
🔗 |
🔗 |
| 52 |
YOLOv4：Optimal Speed and Accuracy of Object Detection |
YOLOv4 |
🔗 |
🔗 |
| 53 |
YOLOv5 |
YOLOv5 |
\ |
🔗 |
| 54 |
YOLOX：Exceeding YOLO Series in 2021 |
YOLOX |
🔗 |
🔗 |
| 55 |
Focal Loss for Dense Object Detection |
Focal Loss，RetinaNet |
🔗 |
🔗 |
| 56 |
RTMDet：An Empirical Study of Designing Real-Time Object Detectors |
RTMDet |
🔗 |
🔗 |
| 57 |
RTMPose：Real-Time Multi-Person Pose Estimation based on MMPose |
RTMPose |
🔗 |
🔗 |
| 58 |
Effective Whole-body Pose Estimation with Two-stages Distillation |
DWPose |
🔗 |
🔗 |
| 59 |
OpenPose：Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields |
OpenPose |
🔗 |
🔗 |
| 60 |
GPT系列论文 |
GPT1，GPT2，GPT3，GPT3.5，InstructGPT，GPT4 |
🔗 |
🔗 |
| 61 |
Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation |
SCAI |
🔗 |
🔗 |
| 62 |
Simple Baselines for Human Pose Estimation and Tracking |
SimpleBaseline |
🔗 |
🔗 |
| 63 |
TaG-Net：Topology-Aware Graph Network for Centerline-Based Vessel Labeling |
TaG-Net，vessel labeling，vessel segmentation |
🔗 |
🔗 |
| 64 |
OverFeat：Integrated Recognition, Localization and Detection using Convolutional Networks |
OverFeat，sliding window |
🔗 |
🔗 |
| 65 |
Bag of Tricks for Image Classification with Convolutional Neural Networks |
ResNet-vc，ResNet-vd |
🔗 |
🔗 |
| 66 |
R-FCN：Object Detection via Region-based Fully Convolutional Networks |
R-FCN |
🔗 |
🔗 |
| 67 |
Deformable Convolutional Networks |
DCN |
🔗 |
🔗 |
| 68 |
A Generic Camera Model and Calibration Method for Conventional, Wide-Angle, and Fish-Eye Lenses |
鱼眼相机校正 |
🔗 |
🔗 |
| 69 |
PP-YOLO：An Effective and Efficient Implementation of Object Detector |
PP-YOLO |
🔗 |
🔗 |
| 70 |
UnitBox：An Advanced Object Detection Network |
UnitBox，IoU loss |
🔗 |
🔗 |
| 71 |
IoU-aware Single-stage Object Detector for Accurate Localization |
IoU-aware loss |
🔗 |
🔗 |
| 72 |
PP-YOLOv2：A Practical Object Detector |
PP-YOLOv2 |
🔗 |
🔗 |
| 73 |
BERT：Pre-training of Deep Bidirectional Transformers for Language Understanding |
BERT |
🔗 |
🔗 |
| 74 |
Group Normalization |
Batch Norm，Layer Norm，Instance Norm，Group Norm |
🔗 |
🔗 |
| 75 |
FCOS：Fully Convolutional One-Stage Object Detection |
FCOS |
🔗 |
🔗 |
| 76 |
Machine Learning for High-Speed Corner Detection |
FAST |
🔗 |
🔗 |
| 77 |
TOOD：Task-aligned One-stage Object Detection |
TOOD |
🔗 |
🔗 |
| 78 |
Generalized Focal Loss：Learning Qualified and Distributed Bounding Boxes for Dense Object Detection |
GFL，QFL，DFL |
🔗 |
🔗 |
| 79 |
BRISK：Binary Robust invariant scalable keypoints |
BRISK |
🔗 |
🔗 |
| 80 |
Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection |
ATSS |
🔗 |
🔗 |
| 81 |
VarifocalNet：An IoU-aware Dense Object Detector |
VFNet，Varifocal Loss，IACS |
🔗 |
🔗 |
| 82 |
PP-YOLOE：An evolved version of YOLO |
PP-YOLOE |
🔗 |
🔗 |
| 83 |
EfficientNet：Rethinking Model Scaling for Convolutional Neural Networks |
EfficientNet |
🔗 |
🔗 |
| 84 |
MobileNets：Efficient Convolutional Neural Networks for Mobile Vision Applications |
MobileNet |
🔗 |
🔗 |
| 85 |
MobileNetV2：Inverted Residuals and Linear Bottlenecks |
MobileNetV2 |
🔗 |
🔗 |
| 86 |
An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection |
VoVNet |
🔗 |
🔗 |
| 87 |
Enriching Variety of Layer-wise Learning Information by Gradient Combination |
PRN |
🔗 |
🔗 |
| 88 |
SSD：Single Shot MultiBox Detector |
SSD |
🔗 |
🔗 |
| 89 |
Scaled-YOLOv4：Scaling Cross Stage Partial Network |
Scaled-YOLOv4，YOLOv4-CSP，YOLOv4-Tiny，YOLOv4-Large |
🔗 |
🔗 |
| 90 |
You Only Learn One Representation：Unified Network for Multiple Tasks |
YOLOR |
🔗 |
🔗 |
| 91 |
Designing Network Design Strategies Through Gradient Path Analysis |
ELAN |
🔗 |
🔗 |
| 92 |
ShuffleNet：An Extremely Efficient Convolutional Neural Network for Mobile Devices |
ShuffleNet |
🔗 |
🔗 |
| 93 |
Squeeze-and-Excitation Networks |
SENet |
🔗 |
🔗 |
| 94 |
ShuffleNet V2：Practical Guidelines for Efficient CNN Architecture Design |
ShuffleNet V2 |
🔗 |
🔗 |
| 95 |
RepVGG：Making VGG-style ConvNets Great Again |
RepVGG |
🔗 |
🔗 |
| 96 |
YOLOv7：Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors |
YOLOv7 |
🔗 |
🔗 |
| 97 |
Generalized Intersection over Union：A Metric and A Loss for Bounding Box Regression |
GIoU |
🔗 |
🔗 |
| 98 |
Distance-IoU Loss：Faster and Better Learning for Bounding Box Regression |
DIoU，CIoU |
🔗 |
🔗 |
| 99 |
SIoU Loss：More Powerful Learning for Bounding Box Regression |
SIoU |
🔗 |
🔗 |
| 100 |
RE-PARAMETERIZING YOUR OPTIMIZERS RATHER THAN ARCHITECTURES |
RepOptimizers，RepOpt-VGG |
🔗 |
🔗 |
| 101 |
NEURAL ARCHITECTURE SEARCH WITH REINFORCEMENT LEARNING |
NAS |
🔗 |
🔗 |