OCR-free Document Understanding Transformer

clovaai/donut 30 Nov 2021

Current Visual Document Understanding (VDU) methods outsource the task of reading text to off-the-shelf Optical Character Recognition (OCR) engines and focus on the understanding task with the OCR outputs.

Optical Character Recognition

564
1.18 stars / hour

PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds

PaddlePaddle/Paddle3D CVPR 2021

The key of PAConv is to construct the convolution kernel by dynamically assembling basic weight matrices stored in Weight Bank, where the coefficients of these weight matrices are self-adaptively learned from point positions through ScoreNet.

3D Point Cloud Classification Point Cloud Classification +1

85
1.08 stars / hour

LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale

timdettmers/bitsandbytes 15 Aug 2022

We develop a procedure for Int8 matrix multiplication for feed-forward and attention projection layers in transformers, which cut the memory needed for inference by half while retaining full precision performance.

Language Modelling Linguistic Acceptability +4

135
0.96 stars / hour

Flow-Guided Transformer for Video Inpainting

hitachinsk/fgt 14 Aug 2022

Especially in spatial transformer, we design a dual perspective spatial MHSA, which integrates the global tokens to the window-based attention.

Video Inpainting

84
0.87 stars / hour

Paint2Pix: Interactive Painting based Progressive Image Synthesis and Editing

1jsingh/paint2pix 17 Aug 2022

In particular, we propose a novel approach paint2pix, which learns to predict (and adapt) "what a user wants to draw" from rudimentary brushstroke inputs, by learning a mapping from the manifold of incomplete human paintings to their realistic renderings.

Image Generation

27
0.83 stars / hour

StyleFaceV: Face Video Generation via Decomposing and Recomposing Pretrained StyleGAN3

arthur-qiu/stylefacev 16 Aug 2022

Notably, StyleFaceV is capable of generating realistic $1024\times1024$ face videos even without high-resolution training videos.

Image Generation Video Generation

68
0.78 stars / hour

Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision

SinicaGroup/Class-agnostic-Few-shot-Object-Counting 20 May 2022

While there are class-agnostic counting methods that can generalise to unseen classes, these methods require reference images to define the type of object to be counted, as well as instance annotations during training.

Object Counting

83
0.71 stars / hour

TotalSegmentator: robust segmentation of 104 anatomical structures in CT images

wasserth/totalsegmentator 11 Aug 2022

Finally, we train a segmentation algorithm on this new dataset.

64
0.59 stars / hour

YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

wongkinyiu/yolov7 6 Jul 2022

YOLOv7 surpasses all known object detectors in both speed and accuracy in the range from 5 FPS to 160 FPS and has the highest accuracy 56. 8% AP among all known real-time object detectors with 30 FPS or higher on GPU V100.

Real-Time Object Detection

4,598
0.58 stars / hour

Can Language Models Make Fun? A Case Study in Chinese Comical Crosstalk

anonno2/crosstalk-generation 2 Jul 2022

However, the humor aspect of natural language is relatively under-investigated, especially in the age of pre-trained language models.

Machine Translation Text Generation

66
0.56 stars / hour