网络结构：
- VGG
- ResNet
- GoogLeNet
- Xception
- DenseNet
- Deformable CNN
- ResNeXt
- DPN
- SENet
- Non-local （CVPR2018）
- Wide Residual Networks
- Learning Transferable Architectures for Scalable Image Recognition
- Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave
- MobileNets
- Bag of Tricks for Image Classification with Convolutional Neural Networks
- Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Network
语义分割：
- FCN
- U-Net
- V-Net
- DeepLab v1、v2
- DeconvNet
- SegNet
- PSPNet
- 3D U-JAPA-Net（MICCAI2018）
- Multi-scale pyramaid of 3D FCNs（MICCAI2018）
- DeepLab v3、v3+
- RefineNet
- FC-DenseNets for Semantic Segmentation
- BiSeNet
- Learning a Discriminative Feature Network for Semantic Segmentation （CVPR2018）
- Context Encoding for Semantic Segmentation（CVPR2018）
- Anatomical Priors in Convolutional Networks for Unsupervised Biomedical Segmentation（CVPR2018）
- VoxResNet
- A Segmentation-aware Deep Fusion Network for Compressed Sensing MRI（ECCV2018）
- FCN+RNN for 3D image segmentation
- Semantic Segmentation using Adversarial Networks
- Revisiting Dilated Convolution: A Simple Approach forWeakly- and Semi- Supervised Semant（CVPR2018）
- Adaptive Affinity Fields for Semantic Segmentation（ECCV2018）
- Focus, Segment and Erase: An Efficient Network for Multi-Label Brain Tumor Segmentation（ECCV2018）
- ExFuse: Enhancing Feature Fusion for Semantic Segmentation（ECCV2018）
- Attention U-Net: Learning Where to Look for the Pancreas
- HyperDense-Net: A hyper-densely connected CNN for multi-modal image segmentation
- Data augmentation using learned transforms for one-shot medical image segmentation（CVPR2019）
- Few-shot 3D Multi-modal Medical Image Segmentation using Generative Adversarial Learning
- FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation（CVPR2019)
- Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net)
- Autofocus Layer for Semantic Segmentation（MICCAI2018）
- Data-Dependent Decoding Enables Flexible Feature Aggregation(CVPR2019)
- Dual Attention Network for Scene Segmentation(CVPR2019)
- H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes
- CE-Net: Context Encoder Network for 2D Medical Image Segmentation
- Adaptive feature recombination and recalibration for semantic segmentation with Fully Convolutional Networks
- High-Resolution Representations for Labeling Pixels and Regions
目标检测：
- SPP
- R-CNN
- Fast R-CNN
- Faster R-CNN
- Mask R-CNN
- R-FCN
- YOLO
- SSD
- FPN
- RetinaNet
- DSFD: Dual Shot Face Detector(CVPR2019)
- YOLACT Real-time Instance Segmentation
- FoveaBox: Beyond Anchor-based Object Detector
机器学习：
RNN：
- CRFasRNN
生成对抗网络：
- GANs
- cGANs
- CycleGANs
- Semantic Segmentation using Adversarial Networks
- Semantic Image Synthesis with Spatially-Adaptive Normalization
自编码器：
炼丹技巧：
TensorFlow实战：
Keras实战：
pytorch实战：
