經典CNN模型+經典圖像語義分割模型總結

5 人贊了文章

Base Network

1. LeNet：LeCun et.al., 1998. Gradient-based learning applied to document recognition
2. AlexNet：Krizhevsky et al.,2012. ImageNet classification with deep convolutional neural networks
3. NIN：Lin et al., 2013. Network in network
4. VGG：Simonvan & Zisserman 2015. Very deep convolutional networks for large-scale image recognition
5. GoogleNet/Inception V1：Szegedy et al., 2014, Going Deeper with Convolutions
6. Inception V2 ：Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
7. Inception V3 ：Rethinking the Inception Architecture for Computer Vision
8. Inception V4 ：Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
9. Xception：https://arxiv.org/abs/1610.02357
10. ResNet：He et al., 2015. Deep residual networks for image recognition
11. ResNeXt
12. DenseNet
13. Wide ResNet
14. DPNet
15. NASNet
16. SENet
17. Capsules

Semantic Segmentation

1、FCN系列：

• FCN：Fully Convolutional Networks for Semantic Segmentation：https://arxiv.org/pdf/1411.4038.pdf
• UNet： Convolutional Networks for Biomedical Image Segmentation：https://arxiv.org/pdf/1505.04597.pdf
• DeconvNet：Learning Deconvolution Network for SemanticSegmentation：https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Noh_Learning_Deconvolution_Network_ICCV_2015_paper.pdf

2、SegNet（segnet erfnet）系列：

• Enet
• SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation：https://arxiv.org/pdf/1511.00561.pdf

3、PSPNet(ICNet)系列：

• PSPNet：Pyramid Scene Parsing Network：https://arxiv.org/pdf/1612.01105.pdf
• ICNet：ICNet for Real-Time Semantic Segmentation on High-Resolution Images

4、Deeplab系列：

• deeplab v1：Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs：https://arxiv.org/pdf/1412.7062.pdf
• deeplab v2：DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs：https://arxiv.org/pdf/1606.00915.pdf
• deeplab v3：Rethinking Atrous Convolution for Semantic Image Segmentation：https://arxiv.org/pdf/1706.05587.pdf
• deeplab v3+：

5、Dilated Convolutions：

• Dilated Convolutions：Multi-Scale Context Aggregation by Dilated Convolutions：https://arxiv.org/pdf/1511.07122.pdf

6、RefineNet

• RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation：https://arxiv.org/pdf/1611.06612.pdf

7、Large Kernel MAtters

• Large Kernel Matters：Improve Semantic Segmentation by Global Convolutional Network：https://arxiv.org/pdf/1703.02719.pdf

8、Mask R-CNN

• Mask R-CNN：https://arxiv.org/pdf/1703.06870.pdf

推薦閱讀：