Trending Research
Background Matting: The World is Your Green Screen
• senguptaumd/Background-Matting
• 
To bridge the domain gap to real imagery with no labeling, we train another matting network guided by the first network and by a discriminator that judges the quality of composites.
Tracking Objects as Points
Nowadays, tracking is dominated by pipelines that perform object detection followed by temporal association, also known as tracking-by-detection.
COVID-CT-Dataset: A CT Scan Dataset about COVID-19
CT scans are promising in providing accurate, fast, and cheap screening and testing of COVID-19.
First Order Motion Model for Image Animation
NeurIPS 2019
• AliaksandrSiarohin/first-order-model
•
To achieve this, we decouple appearance and motion information using a self-supervised formulation.
Proximal Policy Optimization Algorithms
We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent.
Asynchronous Methods for Deep Reinforcement Learning
We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers.
#4 best model for
Atari Games
on Atari 2600 Road Runner
Deep Recurrent Q-Learning for Partially Observable MDPs
Deep Reinforcement Learning has yielded proficient controllers for complex tasks.
Playing Atari with Deep Reinforcement Learning
We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning.
SOTA for Atari Games on Atari 2600 Pong
Weight Uncertainty in Neural Networks
• piEsposito/blitz-bayesian-deep-learning
•
We introduce a new, efficient, principled and backpropagation-compatible algorithm for learning a probability distribution on the weights of a neural network, called Bayes by Backprop.