Research Paper Archive

PS. There are some issues with the math getting rendered in Github's dark mode. We're working on it, but until then we request you to switch to lite mode/open the summary in incognito(which defaults to light mode) to view the paper if you face any difficulty in viewing the math!!

This will be a community-driven repository where people contribute by sharing their thoughts on different research papers they have come across as a simple readme file. This would benefit the contributors by acting as a documentation for future reference and once this archive becomes decently big it would benefit the larger community as a whole. There is no restriction regarding what papers you can add onto this archive - can be old, new anything. Hope this repository gets some good contributions. Happy reading :)

Current Paper Count: 30

To contribute

• Fork the repository
• Add the required files as described below.
• Make a pull request (everything will be merged)

REPOSITORY Layout

.
├── README.md               # Entry point to view all available papers in the archive. 
├── Papers
├──── <PAPER-1> (a folder) `  # Every paper must be inside a folder titled as the paper name
    ├──── assets              # Folder to contain images used in the README file to summarise the paper.
    └──── README.md           # README file containing the summary itself.
├──── <PAPER-2>
    ├──── assets
    └──── README.md
├──── <PAPER-3>
    ├──── assets
    └──── README.md

Contents

• Computer Vision

  • U-Net: Convolutional Networks for Biomedical Image Segmentation
  • UNet++: A Nested U-Net Architecture for Medical Image Segmentation
  • PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
  • StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks
  • StyleGAN: A Style-Based Generator Architecture for Generative Adversarial Networks
  • Image Inpainting - Generative Image Inpainting with Contextual Attention
  • Pix2Pix - Image-to-Image Translation with Conditional Adversarial Networks
  • ResNet - Deep Residual Learning for Image Recognition
  • YOLO - You Only Look Once: Unified, Real-Time Object Detection
  • Semantic Segmentation - Pyramid Scene Parsing Network
  • DINO: Emerging Properties in Self-Supervised Vision Transformers
  • 3D-R2N2_ A Unified Approach for Single and Multi-view 3D Object Reconstruction
  • DeepSDF_ Learning Continuous Signed Distance Functions for Shape Representation
  • Improved Adversarial Systems for 3D Object Generation and Reconstruction
  • Improved Protein Structure Prediction Using Potentials From Deep Learning
  • Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction
  • Learning Implicit Fields for Generative Shape Modeling
  • Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
  • Occupancy Networks_ Learning 3D Reconstruction in Function Space
  • Pix2Vox++_ Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images
  • Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstruction
  • Per-Pixel Classification is Not All You Need for Semantic Segmentation

• Natural Language Processing

  • BERT - Pre-training of Deep Bidirectional Transformers for Language Understanding
  • DrQA - Reading Wikipedia to Answer Open-Domain Questions
  • Knowing When To Look - Adaptive attention for image captioning
  • Meshed-Memory Transformer for Image Captioning

• Reinforcement Learning

  • Asynchronous Methods for Deep Reinforcement Learning
  • DQN - Playing Atari with Deep Reinforcement Learning
  • DRQN - Deep Recurrent Q-Learning for Partially Observable MDPs
  • PPO - Proximal Policy Optimization Algorithms
  • Learning to Paint With Model-based Deep Reinforcement Learning

---

NOTE

• Please ensure that you create an entry point to the summary on the main README FILE (this one).
• Create seperate folders for each paper to add to the repository and keep a seperate folder inside each called assets for any images used in your summary.
• In case of any error in any of the summaries, feel free to open an issue stating the paper name and what you think is the problem with the summary!!