# OCR-free Document Understanding Transformer

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.

564
1.25 stars / hour

# Flow-Guided Transformer for Video Inpainting

14 Aug 2022

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

84
1.04 stars / hour

# StyleFaceV: Face Video Generation via Decomposing and Recomposing Pretrained StyleGAN3

16 Aug 2022

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

68
0.92 stars / hour

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

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.

135
0.83 stars / hour

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

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.

83
0.71 stars / hour

# Paint2Pix: Interactive Painting based Progressive Image Synthesis and Editing

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.

27
0.67 stars / hour

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

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.

4,598
0.59 stars / hour

# Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Models

26 Jul 2022

In RDMs, a set of nearest neighbors is retrieved from an external database during training for each training instance, and the diffusion model is conditioned on these informative samples.

2,830
0.57 stars / hour

# TotalSegmentator: robust segmentation of 104 anatomical structures in CT images

11 Aug 2022

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

64
0.56 stars / hour

# Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning

28 Jan 2022

Existing model-parallel training systems either require users to manually create a parallelization plan or automatically generate one from a limited space of model parallelism configurations.

804
0.49 stars / hour