Trending Research

Background Matting: The World is Your Green Screen

1 Apr 2020senguptaumd/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.

602
2.85 stars / hour

Tracking Objects as Points

2 Apr 2020xingyizhou/CenterTrack

Nowadays, tracking is dominated by pipelines that perform object detection followed by temporal association, also known as tracking-by-detection.

OBJECT DETECTION

395
1.61 stars / hour

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.

3D DEPTH ESTIMATION IMAGE ANIMATION VIDEO RECONSTRUCTION

2,260
0.84 stars / hour

COVID-CT-Dataset: A CT Scan Dataset about COVID-19

30 Mar 2020UCSD-AI4H/COVID-CT

CT scans are promising in providing accurate, fast, and cheap screening and testing of COVID-19.

250
0.69 stars / hour

pycls

30 Mar 2020facebookresearch/pycls

Codebase for Image Classification Research, written in PyTorch.

IMAGE CLASSIFICATION

804
0.59 stars / hour

Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations

27 Mar 2020cuishuhao/BNM

We find by theoretical analysis that the prediction discriminability and diversity could be separately measured by the Frobenius-norm and rank of the batch output matrix.

DOMAIN ADAPTATION

88
0.54 stars / hour

Strip Pooling: Rethinking Spatial Pooling for Scene Parsing

30 Mar 2020Andrew-Qibin/SPNet

Spatial pooling has been proven highly effective in capturing long-range contextual information for pixel-wise prediction tasks, such as scene parsing.

SCENE PARSING

45
0.49 stars / hour

deep-rl-tf2

20 Jul 2017marload/deep-rl-tf2

🐋 Simple implementations of various popular Deep Reinforcement Learning algorithms using TensorFlow2

DOTA 2 POLICY GRADIENT METHODS

104
0.45 stars / hour

Weight Uncertainty in Neural Networks

20 May 2015piEsposito/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.

BAYESIAN INFERENCE

33
0.43 stars / hour

COVID-19 Image Data Collection

25 Mar 2020ieee8023/covid-chestxray-dataset

This paper describes the initial COVID-19 open image data collection.

1,570
0.38 stars / hour