Trending Research

Language Models are Few-Shot Learners

28 May 2020openai/gpt-3

By contrast, humans can generally perform a new language task from only a few examples or from simple instructions - something which current NLP systems still largely struggle to do.

 SOTA for Language Modelling on Penn Treebank (Word Level) (using extra training data)

COMMON SENSE REASONING COREFERENCE RESOLUTION DOMAIN ADAPTATION FEW-SHOT LEARNING LANGUAGE MODELLING NATURAL LANGUAGE INFERENCE QUESTION ANSWERING SENTENCE COMPLETION UNSUPERVISED MACHINE TRANSLATION WORD SENSE DISAMBIGUATION

1,217
8.19 stars / hour

End-to-End Object Detection with Transformers

26 May 2020facebookresearch/detr

We present a new method that views object detection as a direct set prediction problem.

OBJECT DETECTION PANOPTIC SEGMENTATION

2,710
7.71 stars / hour

TensorflowTTS

NeurIPS 2019 dathudeptrai/TensorflowTTS

:stuck_out_tongue_closed_eyes: TensorflowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2

SPEECH SYNTHESIS

86
1.63 stars / hour

VIBE: Video Inference for Human Body Pose and Shape Estimation

11 Dec 2019mkocabas/VIBE

Human motion is fundamental to understanding behavior.

 SOTA for 3D Human Pose Estimation on 3DPW (using extra training data)

3D HUMAN POSE ESTIMATION 3D POSE ESTIMATION MOTION CAPTURE

1,104
0.80 stars / hour

Variational quantum Gibbs state preparation with a truncated Taylor series

18 May 2020PaddlePaddle/Quantum

By performing numerical experiments, we show that shallow parameterized circuits with only one additional qubit can be trained to prepare the Ising chain and spin chain Gibbs states with a fidelity higher than 95%.

QUANTUM MACHINE LEARNING

156
0.55 stars / hour
4,112
0.53 stars / hour

Point2Mesh: A Self-Prior for Deformable Meshes

22 May 2020ranahanocka/point2mesh

We optimize the network weights to deform an initial mesh to shrink-wrap a single input point cloud.

180
0.41 stars / hour

Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis

17 May 2020Rudrabha/Lip2Wav

In this work, we explore the task of lip to speech synthesis, i. e., learning to generate natural speech given only the lip movements of a speaker.

LIP READING SPEAKER-SPECIFIC LIP TO SPEECH SYNTHESIS SPEECH SYNTHESIS

91
0.38 stars / hour

TabNet: Attentive Interpretable Tabular Learning

ICLR 2020 dreamquark-ai/tabnet

We propose a novel high-performance and interpretable canonical deep tabular data learning architecture, TabNet.

DECISION MAKING FEATURE SELECTION SELF-SUPERVISED LEARNING UNSUPERVISED REPRESENTATION LEARNING

156
0.33 stars / hour

ResNeSt: Split-Attention Networks

19 Apr 2020zhanghang1989/ResNeSt

While image classification models have recently continued to advance, most downstream applications such as object detection and semantic segmentation still employ ResNet variants as the backbone network due to their simple and modular structure.

IMAGE CLASSIFICATION INSTANCE SEGMENTATION OBJECT DETECTION PANOPTIC SEGMENTATION

1,744
0.33 stars / hour