CV三大顶级会议：ICCV ECCV CVPR
cv baseline
AlexNet:ImageNet Classification with Deep Convolutional Neural Networks 基于深度卷积神经网络的图像分类
VGG：VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION 大规模图像识别的深度卷积神经网络 LCLR2015
GoogLeNet:Going deeper with convolutions 更深的卷积神经网络 CVPR2015
GoogLeNet-V2:Batch Normalization: Accelerating Deep Network Training b y Reducing Internal Covariate Shift批标准化:缓解内部协变量偏移加快深度卷积神经网络训练
GoogLeNet-V3:Rethinking the Inception Architecture for Computer Vision重新思考计算机视觉中的Inception结构
ResNet:Deep Residual Learning for Image Recognition图像识别中的深度残差学习网络
GoogLeNet-V4:Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning Inception-v4,Inception-Resnet,残差连接对模型训练的影响
ResNeXt:Aggregated Residual Transformations for Deep Neural Networks 深度神经网络中的残差聚合变换 CVPR2017
DenseNet:Densely Connected Convolutional Networks 稠密连接的卷积神经网络 CVPR2019 best paper
Senet:Squeeze-and-Excitation Networks CVPR2018
OCR:
CRNN:An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition CVPR2015
Attention OCR:Attention-based Extraction of Structured Information from Street View Imagery CVPR2017
GAN:
GAN:Generative Adversarial Nets 生成式对抗网络 NIPS2014
CGAN:Conditional Generative Adversarial Nets 条件生成式对抗网络 ArXiv2014
DCGAN:UNSUPERVISED REPRESENTATION LEARNING WITH DEEP CONVOLUTIONAL GENERATIVE ADVERSARIAL NETWORKS深度卷积生成式对抗网络 ICLR2016
ITGAN：Improved Techniques for Training GANs GAN的训练技巧 NIPS2016
Pix2Pix:Image-to-Image Translation with Conditional Adversarial Networks 用于图像翻译的条件生成式对抗网络 CVPR2017
CycleGAN:Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks用于非配对图像翻译的循环一致性对抗网络 CVPR2017
ProGAN:PROGRESSIVE GROWING OF GANS FOR IMPROVED QUALITY, STABILITY, AND VARIATION提升生成质量、稳定性和多样性的渐进式增长生成对抗网络 ICLR2018
StackGAN:StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks使用堆叠的生成式对抗网络进行文本到照片级图像的合成 ICCV2017
BigGAN:LARGE SCALE GAN TRAINING FOR HIGH FIDELITY NATURAL IMAGE SYNTHESIS训练大规模生成式对抗网络用于高保真自然图像合成 ICLR2019
StyleGAN:A Style-Based Generator Architecture for Generative Adversarial Networks 生成式对抗网络中一种基于样式的生成器架构 CVPR2019
目标检测：
YOLO：v1:You Only Look Once: Unified, Real- Time Object Detect CVPR2016
v2:YOLO9000: Better, Faster, Stronger CVPR2017
v3：YOLOv3: An Incremental Improvement arXiv2018
v4:
SSD:SSD: Single Shot MultiBox Detector ECCV2016
fpn:Feature Pyramid Networks for Object Detection CVPR2017
RetinaNet:Focal Loss for Dense Object Detection ICCV2017
Faster RCNN:Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (Advances in Neural Information Processing Systems, 2015)
MASK RCNN:Mask R-CNN 基于区域候选网络的目标分割方法 ICCV2017
FCOS:FCOS: Fully Convolutional One-Stage Object Detection 一种全卷积单阶段目标检测方法 ICCV2019
EfficientDet:EfficientDet: Scalable and Efficient Object Detectio可扩展且高效的目标检测算法 CVPR2020
cascade rcnn:Cascade R-CNN: Delving into High Quality Object Detection一种致力于高质量目标检测的方法 CVPR2018
强化学习：
todo
图像分割：
FCN:Fully Convolutional Networks for Semantic Segmentation 语义分割中的全卷积网络 CVPR PAMI
FusionNet: A deep fully residual convolutional neural network for image segmentation in connectomics
U-Net: Convolutional Networks for Biomedical Image Segmentation
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation CVPR2015
DeconvNet:Learning Deconvolution Network for Semantic Segmentation
deeplap-v1 :Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs ICLR2015
v2: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs TPAMI2017
v3:Rethinking Atrous Convolution for Semantic Image Segmentation
v3+:Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation ECCV2018
GCN:Large Kernel Matters —— Improve Semantic Segmentation by Global Convolutional Network CVPR2017
DFN:Learning a Discriminative Feature Network for Semantic Segmentation CVPR2018
:ExFuse: Enhancing Feature Fusion for Semantic Segmentation ECCV2018
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation CVPR2016
LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation CVPR2017
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation ECCV2018
DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation CVPR2019
RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation arXiv2018
RDFNet: RGB-D Multi-level Residual Feature Fusion for Indoor Semantic Segmentation ICCV2017
RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation CVPR2017
Light-Weight RefineNet for Real-Time Semantic Segmentation BMVC2018
轻量化网络：
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications 基于移动视觉应用的高效卷积神经网络 CVPR2017
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices 适用于移动设备的极其高效的卷积神经网络 CVPR2018
SQUEEZENET: ALEXNET-LEVEL ACCURACY WITH 50X FEWER PARAMETERS AND <0.5MB MODEL SIZE AlexNet 级精度，参数量减少 50 倍，模型小于0.5MB ICLR2017
Xception: Deep Learning with Depthwise Separable Convolutions 基于深度可分离卷积的深度学习网络 CVPR2017
KD:Distilling the Knowledge in a Neural Network 在神经网络中进行知识蒸馏 NIPS2014
attention-transfer:PAYING MORE ATTENTION TO ATTENTION: IMPROVING THE PERFORMANCE OF CONVOLUTIONAL NEURAL NETWORKS VIA ATTENTION TRANSFER通过注意力转移提升神经网络性能ICLR2017
Learning both Weights and Connections for Efficient Neural Networks 为高效神经网络同时学习权重和连接 NIPS2015
Learning Efficient Convolutional Networks through Network Slimming
PRUNING CONVOLUTIONAL NEURAL NETWORKS FOR RESOURCE EFFICIENT INFERENC 为了进行能源高效推理对CNN剪枝 ICLR2017