Trending Research

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

2,153
14.42 stars / hour

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

538
11.27 stars / hour

Big Transfer (BiT): General Visual Representation Learning

24 Dec 2019google-research/big_transfer

We conduct detailed analysis of the main components that lead to high transfer performance.

 SOTA for Image Classification on ObjectNet (Bounding Box) (using extra training data)

FEW-SHOT LEARNING FINE-GRAINED IMAGE CLASSIFICATION REPRESENTATION LEARNING

544
1.41 stars / hour

Surfboard: Audio Feature Extraction for Modern Machine Learning

18 May 2020novoic/surfboard

We introduce Surfboard, an open-source Python library for extracting audio features with application to the medical domain.

225
1.18 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.

144
1.09 stars / hour

Instance-aware Image Colorization

21 May 2020ericsujw/InstColorization

Previous methods leverage the deep neural network to map input grayscale images to plausible color outputs directly.

COLORIZATION

182
0.72 stars / hour

Skeleton-Aware Networks for Deep Motion Retargeting

12 May 2020DeepMotionEditing/deep-motion-editing

In other words, our operators form the building blocks of a new deep motion processing framework that embeds the motion into a common latent space, shared by a collection of homeomorphic skeletons.

MOTION CAPTURE MOTION RETARGETING MOTION SYNTHESIS

267
0.69 stars / hour

Unpaired Motion Style Transfer from Video to Animation

12 May 2020DeepMotionEditing/deep-motion-editing

In this paper, we present a novel data-driven framework for motion style transfer, which learns from an unpaired collection of motions with style labels, and enables transferring motion styles not observed during training.

3D RECONSTRUCTION MOTION SYNTHESIS STYLE TRANSFER

267
0.69 stars / hour

Analyzing and Improving the Image Quality of StyleGAN

3 Dec 2019rosasalberto/StyleGAN2-TensorFlow-2.x

Overall, our improved model redefines the state of the art in unconditional image modeling, both in terms of existing distribution quality metrics as well as perceived image quality.

IMAGE GENERATION

38
0.57 stars / hour