awesome-deep-learning-mustreads
Must-read papers and must-known concepts
https://github.com/lrunaways/awesome-deep-learning-mustreads
Last synced: 2 days ago
JSON representation
-
[Architectures](https://github.com/lrunaways/awesome-deep-learning-mustreads/blob/master/topics/Architectures.rst)
- Dilated Residual Networks 28 May 2017
- Review: Inception-v3 Sep 10 2018
- Dilated Residual Networks 28 May 2017
- Attention Is All You Need [6 Dec 2017
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks 28 May 2019
- Attention Is All You Need [6 Dec 2017
- Review: Inception-v3 Sep 10 2018
-
[Training](https://github.com/lrunaways/awesome-deep-learning-mustreads/blob/master/topics/Training.rst)
- Multi-GPU Training of ConvNets 18 Feb 2014
- The Effectiveness of Data Augmentation in Image Classification using Deep Learning 13 Dec 2017
- Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes 30 Jul 2018
- MIXED PRECISION TRAINING 15 Feb 2018
- Stochastic Weight Averaging
- A Recipe for Training Neural Networks Apr 25 2019
- Multi-GPU Training of ConvNets 18 Feb 2014
- The Effectiveness of Data Augmentation in Image Classification using Deep Learning 13 Dec 2017
- Parallel and Distributed Deep Learning
- Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis 15 Sep 2018
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour 30 Apr 2018
- Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes 30 Jul 2018
- MIXED PRECISION TRAINING 15 Feb 2018
- A Survey on Distributed Machine Learning 20 Dec 2019
- NVIDIA Deep Learning Performance
- Stochastic Weight Averaging
- Bag of Tricks for Image Classification with Convolutional Neural Networks 5 Dec 2018
- Training Neural Nets on Larger Batches: Practical Tips for 1-GPU, Multi-GPU & Distributed setups
- Stochastic Weight Averaging
- Training Generative Adversarial Networks with Limited Data 7 Oct 2020
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis 15 Sep 2018
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour 30 Apr 2018
- Stochastic Weight Averaging
- Bag of Tricks for Image Classification with Convolutional Neural Networks 5 Dec 2018
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
- Stochastic Weight Averaging
-
[Computer vision](https://github.com/lrunaways/awesome-deep-learning-mustreads/blob/master/topics/Computer_vision.rst)
-
[Transfer learning](https://github.com/lrunaways/awesome-deep-learning-mustreads/blob/master/topics/Transfer_learning.rst)
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
- Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
-
[GANs](https://github.com/lrunaways/awesome-deep-learning-mustreads/blob/master/topics/GANs.rst)
- LARGE SCALE GAN TRAINING FOR HIGH FIDELITY NATURAL IMAGE SYNTHESIS 25 Feb 2019
- Generative Adversarial Networks 10 Jun 2014
- Conditional Generative Adversarial Nets 6 Nov 2014
- Improved Techniques for Training GANs 10 Jun 2016
- Deeplearning.ai specialization: Generative Adversarial Networks
- Deep Convolutional Generative Adversarial Networks 19 Nov 2015
- Wasserstein GAN 6 Dec 2017
- Improved Training of Wasserstein GANs 31 Mar 2017
- From GAN to WGAN 20 Aug 2017
- Conditional Image Synthesis with Auxiliary Classifier GANs 20 Jul 2017
- GANs for Biological Image Synthesis 12 Sep 2017
- PROGRESSIVE GROWING OF GANS FOR IMPROVED QUALITY, STABILITY, AND VARIATION 26 Feb 2018
- Image-to-Image Translation with Conditional Adversarial Networks 26 Nov 2018
- GAN DISSECTION: VISUALIZING AND UNDERSTANDING GENERATIVE ADVERSARIAL NETWORKS 8 Dec 2018
- SPECTRAL NORMALIZATION FOR GENERATIVE ADVERSARIAL NETWORKS 16 Feb 2018
- DATA AUGMENTATION GENERATIVE ADVERSARIAL NETWORKS 21 Mar 2018
- High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs 20 Aug 2018
- Self-Attention Generative Adversarial Networks 14 Jun 2019
- LARGE SCALE GAN TRAINING FOR HIGH FIDELITY NATURAL IMAGE SYNTHESIS 25 Feb 2019
- A Large-Scale Study on Regularization and Normalization in GANs 14 May 2019
- A Style-Based Generator Architecture for Generative Adversarial Networks 29 Mar 2019
- Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints 16 Aug 2019
- Analyzing and Improving the Image Quality of StyleGAN 23 Mar 2020
- Training Generative Adversarial Networks with Limited Data 7 Oct 2020
- Interpreting the Latent Space of GANs for Semantic Face Editing 25 Jul 2019
- Fast Fréchet Inception Distance 29 Sep 2020
- Pros and Cons of GAN Evaluation Measures 9 Feb 2018
- Large Scale GAN Training for High Fidelity Natural Image Synthesis 28 Sep 2018
- HYPE: A Benchmark for Human eYe Perceptual Evaluation of Generative Models 1 Apr 2019
- Improved Precision and Recall Metric for Assessing Generative Models 15 Apr 2019
- GANILLA: Generative Adversarial Networks for Image to Illustration Translation 13 Feb 2020
- Image Augmentations for GAN Training 4 Jun 2020
- Navigating the GAN Parameter Space for Semantic Image Editing 1 Dec 2020
- Improved Techniques for Training GANs 10 Jun 2016
- DATA AUGMENTATION GENERATIVE ADVERSARIAL NETWORKS 21 Mar 2018
- Wasserstein GAN 6 Dec 2017
- SPECTRAL NORMALIZATION FOR GENERATIVE ADVERSARIAL NETWORKS 16 Feb 2018
- A Large-Scale Study on Regularization and Normalization in GANs 14 May 2019
- A Style-Based Generator Architecture for Generative Adversarial Networks 29 Mar 2019
- Analyzing and Improving the Image Quality of StyleGAN 23 Mar 2020
- PROGRESSIVE GROWING OF GANS FOR IMPROVED QUALITY, STABILITY, AND VARIATION 26 Feb 2018
- GANs for Biological Image Synthesis 12 Sep 2017
- GAN DISSECTION: VISUALIZING AND UNDERSTANDING GENERATIVE ADVERSARIAL NETWORKS 8 Dec 2018
- Navigating the GAN Parameter Space for Semantic Image Editing 1 Dec 2020
- Fast Fréchet Inception Distance 29 Sep 2020
-
[Other](https://github.com/lrunaways/awesome-deep-learning-mustreads/blob/master/topics/Other.rst)
-
[Blogs](https://github.com/lrunaways/awesome-deep-learning-mustreads/blob/master/topics/blogs)
- Towards data science
- Towards data science
- Distill blog
- Neurohive
- Towards data science
- Implicit Neural Representations with Periodic Activation Functions
- Stylized Neural Painting
- A Neural Algorithm of Artistic Style
- Towards data science
- Towards data science
- OpenAI blog
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Implicit Neural Representations with Periodic Activation Functions
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Google AI blog
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Stylized Neural Painting
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Towards data science
- Neurohive
- Towards data science
- Towards data science
-
[Theory](https://github.com/lrunaways/awesome-deep-learning-mustreads/blob/master/topics/Theory.rst)
- Deconvolution and Checkerboard Artifacts 2016
- UNDERSTANDING DEEP LEARNING REQUIRES RETHINKING GENERALIZATION 26 Feb 2017
- Emergence of Invariance and Disentanglement in Deep Representations 28 Jun 2018
- Averaging Weights Leads to Wider Optima and Better Generalization 25 Feb 2019
- Towards a Mathematical Understanding of Neural Network-Based Machine Learning 1 Oct 2020
- Towards a Mathematical Understanding of Neural Network-Based Machine Learning 1 Oct 2020
- Emergence of Invariance and Disentanglement in Deep Representations 28 Jun 2018
- Averaging Weights Leads to Wider Optima and Better Generalization 25 Feb 2019
- UNDERSTANDING DEEP LEARNING REQUIRES RETHINKING GENERALIZATION 26 Feb 2017
Categories
[Transfer learning](https://github.com/lrunaways/awesome-deep-learning-mustreads/blob/master/topics/Transfer_learning.rst)
88
[Blogs](https://github.com/lrunaways/awesome-deep-learning-mustreads/blob/master/topics/blogs)
80
[Training](https://github.com/lrunaways/awesome-deep-learning-mustreads/blob/master/topics/Training.rst)
71
[GANs](https://github.com/lrunaways/awesome-deep-learning-mustreads/blob/master/topics/GANs.rst)
45
[Theory](https://github.com/lrunaways/awesome-deep-learning-mustreads/blob/master/topics/Theory.rst)
9
[Other](https://github.com/lrunaways/awesome-deep-learning-mustreads/blob/master/topics/Other.rst)
7
[Architectures](https://github.com/lrunaways/awesome-deep-learning-mustreads/blob/master/topics/Architectures.rst)
7
[Computer vision](https://github.com/lrunaways/awesome-deep-learning-mustreads/blob/master/topics/Computer_vision.rst)
4
Sub Categories
Keywords