Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/hhhhhhao/paper-notes

Notes for paper
https://github.com/hhhhhhao/paper-notes

Last synced: 23 days ago
JSON representation

Notes for paper

Awesome Lists containing this project

README 

        
# Paper-Notes

The notes are writen in Latex syntax.



## Content



### Image Recognization

1. Deep Residual Learning for Image Recognization [[note](./Deep-Residual-Learning-for-Image-Recognition/ResNet.md)][[paper](https://arxiv.org/abs/1512.03385)]

2. Identity Mappings in Deep Residual Networks [[note](./Identity-Mappings-in-Deep-Residual-Networks/PreAct-ResNet.md)[paper](https://arxiv.org/abs/1603.05027)]

3. Wide Residual Networks [[note](./Wide-Residual-Networks/wideResNet.md) [paper](https://arxiv.org/abs/1605.07146)]

4. Densely Connected Convolutional Networks [[note](./Densely-Connected-Convolutional-Networks/DenseNet.md)][[paper](https://arxiv.org/abs/1608.06993)]



### Semi-Supervised Learning



1. Temporal Ensembling for Semi-Supervised Learning [[paper](https://arxiv.org/abs/1610.02242)[note][./Temporal-Ensembling-for-Semi-Supervised-learning/TE.md]]

2. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results [[paper](https://papers.nips.cc/paper/6719-mean-teachers-are-better-role-models-weight-averaged-consistency-targets-improve-semi-supervised-deep-learning-results.pdf) [note](./Mean-Teachers-Are-Better-Role-Models- Weight-Averaged-Consistency-Targets -mprove-Semi-Supervised-Deep-Learning-Results/Mean-T.md)]



### CNN Architecture

1. Network in Network [[note](./Network-in-Network/NIN.md)][[paper](https://arxiv.org/abs/1312.4400)]

2. Non-Local Neural Networks [[note](./Non-Local Neural Networks/NL.md)[paper](https://arxiv.org/abs/1711.07971)]



### CNN Viualization

1. Deep Inside Convolutional Networks Visualising Image Classification Models and Saliency Maps [[note](./Deep-Inside-Convolutional-Networks-Visualising-Imag



### Train Strategy：

1. Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks [[note][./Filter-Response-Normalization-Layer-Eliminating-Batch-Dependence-in-the-Training-of-Deep-Neural-Networks/FRN.md][paper][https://arxiv.org/abs/1911.09737]]



### Total



1. Conditional Generative Adversarial Nets [[note](./Conditional-Generative-Adversarial-Nets/cGANs.md)][[paper](https://arxiv.org/abs/1411.1784)]

2. Deep Image Prior [[note](./Deep-Image-Prior/Deep-Image-Prior.md)][[paper](https://dmitryulyanov.github.io/deep_image_prior)]

3. Deep Inside Convolutional Networks Visualising Image Classification Models and Saliency Maps [[note](./Deep-Inside-Convolutional-Networks-Visualising-Image-Classification-Models-and-Saliency-Maps/CNN-Vis-Saliency-Maps.md)][[paper](https://arxiv.org/abs/1312.6034)]

4. Deep Residual Learning for Image Recognization [[note](./Deep-Residual-Learning-for-Image-Recognition/ResNet.md)][[paper](https://arxiv.org/abs/1512.03385)]

5. Densely Connected Convolutional Networks [[note](./Densely-Connected-Convolutional-Networks/DenseNet.md)][[paper](https://arxiv.org/abs/1608.06993)]

6. Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World [[note](./Domain-Randomization-for-Transferring-Deep-Neural-Networks-from-Simulation-to-the-Real-World/Domain-Randomization.md)][[paper](https://arxiv.org/abs/1703.06907)]

7. NIPS 2016 Tutorial: Generative Adversarial Networks  [[note](./GAN-Tutorial/GAN.md)][[paper](https://arxiv.org/abs/1701.00160)]

8. Generative Adversarial Nets [[note](./Generative-Adversarial-Nets/GAN.md)][[paper](https://arxiv.org/abs/1406.2661)]

9. Going Deeper with Convolutions [[note](./Going-Deeper-with-Convolutions/GoogleNet.md)][[paper](https://arxiv.org/abs/1409.4842)]

10. ImageNet Classification with Deep Convolutional Neural Networks [[note](./ImageNet-Classification-with-Deep-Convolutional-Neural-Networks/AlexNet.md)][[paper](https://www.nvidia.cn/content/tesla/pdf/machine-learning/imagenet-classification-with-deep-convolutional-nn.pdf)]

11. Image to Image Translation with Conditional Adversarial Networks [[note](./Image-to-Image-Translation-with-Conditional-Adversarial-Networks/Pix2Pix.md)][[paper](https://phillipi.github.io/pix2pix/)]

12. InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets [[note](./InfoGAN-Interpretable-Representation-Learning-by-Information-Maximizing-Generative-Adversarial-Nets/InfoGAN.md)][[paper](https://arxiv.org/abs/1606.03657)]

13. Intriguing Properties of Neural Networks [[note](./Intriguing-Properties-of-Neural-Networks/Adversarial-Examples.md)][[paper](https://arxiv.org/abs/1312.6199)]

14. Least Squares Generative Adversarial Networks [[note](./Least-Squares-Generative-Adversarial-Networks/LSGANs.md)][[paper](https://arxiv.org/abs/1611.04076)]

15. Network in Network [[note](./Network-in-Network/NIN.md)][[paper](https://arxiv.org/abs/1312.4400)]

16. Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial

    Network [[note](./Photo-Realistic-Single-Image-Super-Resolution-Using-a-Generative-Adversarial-Network/SRGAN.md)][[paper](https://arxiv.org/pdf/1609.04802.pdf)]

17. Show and Tell: A Neural Image Caption Generato [[note](./Show-and-Tell-A-Neural-Image-Caption-Generator/Show-and-Tell.md)][[paper](https://arxiv.org/abs/1411.4555)]

18. Stacked Generative Adversarial Networks [[note](./Stacked-Generative-Adversarial-Networks/SGAN.md)][[paper](https://arxiv.org/pdf/1612.04357.pdf)]

19. Striving for Simplicity: The All Convolutional Nets [[note](./Striving-for-Simplicity-The-All-Convolutional-Net/All-CNNs.md)][[paper](https://arxiv.org/abs/1412.6806)]

20. Spectral Normalization for GANs [[note](./Spectral-Normalization-for-GANS/Spectral-Norm.md)][[paper](https://arxiv.org/pdf/1802.05957.pdf)]

21. Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net [[note](./Two-at-Once-Enhancing-Learning-and-Generalization-Capacities-via-IBN-Net/IBN-Net.md)][[paper](https://arxiv.org/abs/1807.09441)]

22. Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization [[note](./Training-Deep-Networks-with-Synthetic-Data-Bridging-the-Reality-Gap-by-Domain-Randomization/Domain-Randomization-Object-Detection.md)] [[paper](https://www.semanticscholar.org/paper/Training-Deep-Networks-With-Synthetic-Data%3A-the-Gap-Tremblay-Prakash/c636cd6eba286357fe807c0ca4b02c3b9b7b5619?navId=citing-papers)]

23. U-Net: Convolutional Networks for Biomedical Image Segmentation [[note](./U-Net-Convolutional-Networks-for-Biomedical-Image-Segmentation/U-net.md)][[paper](https://arxiv.org/pdf/1505.04597.pdf)]

24. Unpaired Image to Image Translation using Cycle Consistent Adversarial Networks [[note](./Unpaired-Image-to-Image-Translation-using-Cycle-Consistent-Adversarial-Networks/cycleGAN.md)][[paper](https://arxiv.org/pdf/1703.10593.pdf)]

25. Unsupervised Representation Learning With Deep Convolutional Genertive Adversarial Networks [[note](DCGAN.md)][[paper](https://arxiv.org/abs/1511.06434)]

26. Very Deep Convolutional Networks for Large Scale Image Recognization [[note](./Very-Deep-Convolutional-Networks-for-Large-Scale-Image-Recognization/VGG.md)][[paper](https://arxiv.org/pdf/1409.1556.pdf)]

27. Visualizing and Understanding CNNs [[note](./Visualizing-and-Understanding-CNNs/Deconv-Vis.md)][[paper](https://cs.nyu.edu/~fergus/papers/zeilerECCV2014.pdf)]