2020: A Year Full of Amazing AI papers- A Review

A curated list of the latest breakthroughs in AI by release date with a clear video explanation, link to a more in-depth article, and code

Even with everything that happened in the world this year, we still had the chance to see a lot of amazing research come out. Especially in the field of artificial intelligence. More, many important aspects were highlighted this year, like the ethical aspects, important biases, and much more. Artificial intelligence and our understanding of the human brain and its link to AI is constantly evolving, showing promising applications in the soon future.

Here are the most interesting research papers of the year, in case you missed any of them. In short, it is basically a curated list of the latest breakthroughs in AI and Data Science by release date with a clear video explanation, link to a more in-depth article, and code (if applicable). Enjoy the read!

The complete reference to each paper is listed at the end of this repository.

Maintainer - louisfb01

Subscribe to my newsletter - The latest updates in AI explained every week.

🆕 Check the 2021 repo!

Feel free to message me any great papers I missed to add to this repository on bouchard.lf@gmail.com

Tag me on Twitter @Whats_AI or LinkedIn @Louis (What's AI) Bouchard if you share the list!

Watch a complete 2020 rewind in 15 minutes

---

If you are interested in computer vision research, here is another great repository for you:

The top 10 computer vision papers in 2020 with video demos, articles, code, and paper reference.

Top 10 Computer Vision Papers 2020

---

👀 If you'd like to support my work and use W&B (for free) to track your ML experiments and make your work reproducible or collaborate with a team, you can try it out by following this guide! Since most of the code here is PyTorch-based, we thought that a QuickStart guide for using W&B on PyTorch would be most interesting to share.

👉Follow this quick guide, use the same W&B lines in your code or any of the repos below, and have all your experiments automatically tracked in your w&b account! It doesn't take more than 5 minutes to set up and will change your life as it did for me! Here's a more advanced guide for using Hyperparameter Sweeps if interested :)

🙌 Thank you to Weights & Biases for sponsoring this repository and the work I've been doing, and thanks to any of you using this link and trying W&B!

---

The Full List

• YOLOv4: Optimal Speed and Accuracy of Object Detection [1]
• DeepFaceDrawing: Deep Generation of Face Images from Sketches [2]
• Learning to Simulate Dynamic Environments with GameGAN [3]
• PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models [4]
• Unsupervised Translation of Programming Languages [5]
• PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization [6]
• High-Resolution Neural Face Swapping for Visual Effects [7]
• Swapping Autoencoder for Deep Image Manipulation [8]
• GPT-3: Language Models are Few-Shot Learners [9]
• Learning Joint Spatial-Temporal Transformations for Video Inpainting [10]
• Image GPT - Generative Pretraining from Pixels [11]
• Learning to Cartoonize Using White-box Cartoon Representations [12]
• FreezeG: Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs [13]
• Neural Re-Rendering of Humans from a Single Image [14]
• I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image [15]
• Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments [16]
• RAFT: Recurrent All-Pairs Field Transforms for Optical Flow [17]
• Crowdsampling the Plenoptic Function [18]
• Old Photo Restoration via Deep Latent Space Translation [19]
• Neural circuit policies enabling auditable autonomy [20]
• Lifespan Age Transformation Synthesis [21]

---

YOLOv4: Optimal Speed and Accuracy of Object Detection [1]

This 4th version has been recently introduced in April 2020 by Alexey Bochkovsky et al. in the paper "YOLOv4: Optimal Speed and Accuracy of Object Detection". The main goal of this algorithm was to make a super-fast object detector with high quality in terms of accuracy.

• Short Video Explanation:

• The YOLOv4 algorithm | Introduction to You Only Look Once, Version 4 | Real-Time Object Detection - Short Read
• YOLOv4: Optimal Speed and Accuracy of Object Detection - The Paper
• Click here for the Yolo v4 code - The Code

DeepFaceDrawing: Deep Generation of Face Images from Sketches [2]

You can now generate high-quality face images from rough or even incomplete sketches with zero drawing skills using this new image-to-image translation technique! If your drawing skills as bad as mine you can even adjust how much the eyes, mouth, and nose will affect the final image! Let's see if it really works and how they did it.

• Short Video Explanation:

• AI Generates Real Faces From Sketches! - Short Read
• DeepFaceDrawing: Deep Generation of Face Images from Sketches - The Paper
• Click here for the DeepFaceDrawing code - The Code

Learning to Simulate Dynamic Environments with GameGAN [3]

GameGAN, a generative adversarial network trained on 50,000 PAC-MAN episodes, produces a fully functional version of the dot-munching classic without an underlying game engine.

• Short Video Explanation:

• 40 Years on, PAC-MAN Recreated with AI by NVIDIA Researchers - Short Read
• Learning to Simulate Dynamic Environments with GameGAN - The Paper
• Click here for the GameGAN code - The Code

PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models [4]

This new algorithm transforms a blurry image into a high-resolution image! It can take a super low-resolution 16x16 image and turn it into a 1080p high definition human face! You don't believe me? Then you can do just like me and try it on yourself in less than a minute! But first, let's see how they did that.

• Short Video Explanation:

• This AI makes blurry faces look 60 times sharper - Short Read
• PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models - The Paper
• Click here for the PULSE code - The Code

Unsupervised Translation of Programming Languages [5]

This new model converts code from a programming language to another without any supervision! It can take a Python function and translate it into a C++ function, and vice-versa, without any prior examples! It understands the syntax of each language and can thus generalize to any programming language! Let's see how they did that.

• Short Video Explanation:

• This AI translates code from a programming language to another | Facebook TransCoder Explained - Short Read
• Unsupervised Translation of Programming Languages - The Paper
• Click here for the Transcoder code - The Code

PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization [6]

This AI Generates 3D high-resolution reconstructions of people from 2D images! It only needs a single image of you to generate a 3D avatar that looks just like you, even from the back!

• Short Video Explanation:

• AI Generates 3D high-resolution reconstructions of people from 2D images | Introduction to PIFuHD - Short Read
• PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization - The Paper
• Click here for the PiFuHD code - The Code

High-Resolution Neural Face Swapping for Visual Effects [7]

Researchers at Disney developed a new High-Resolution Face Swapping algorithm for Visual Effects in the paper of the same name. It is capable of rendering photo-realistic results at megapixel resolution. Working for Disney, they are most certainly the best team for this work. Their goal is to swap the face of a target actor from a source actor while maintaining the actor's performance. This is incredibly challenging and is useful in many circumstances, such as changing the age of a character, when an actor is not available, or even when it involves a stunt scene that would be too dangerous for the main actor to perform. The current approaches require a lot of frame-by-frame animation and post-processing by professionals.

• Short