Diffusion Models Beat GANs on Image Synthesis

11 May 2021

Finally, we find that classifier guidance combines well with upsampling diffusion models, further improving FID to 3. 85 on ImageNet 512$\times$512.

226
3.68 stars / hour

RealFormer: Transformer Likes Residual Attention

21 Dec 2020

Transformer is the backbone of modern NLP models.

775
1.73 stars / hour

PAFNet: An Efficient Anchor-Free Object Detector Guidance

28 Apr 2021

Therefore, a trade-off between effectiveness and efficiency is necessary in practical scenarios.

Ranked #1 on Object Detection on COCO test-dev (AP metric)

3,614
1.45 stars / hour

Sensitive Data Detection with High-Throughput Neural Network Models for Financial Institutions

17 Dec 2020

However, the application of sensitive entity detection for production systems in financial institutions has not been well explored due to the lack of publicly available, labeled datasets.

307
1.37 stars / hour

12 Apr 2021

In this paper, we explore the open-domain sketch-to-photo translation, which aims to synthesize a realistic photo from a freehand sketch with its class label, even if the sketches of that class are missing in the training data.

939
1.06 stars / hour

Self-Supervised Learning with Swin Transformers

10 May 2021

We are witnessing a modeling shift from CNN to Transformers in computer vision.

103
1.06 stars / hour

LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference

2 Apr 2021

We design a family of image classification architectures that optimize the trade-off between accuracy and efficiency in a high-speed regime.

213
0.90 stars / hour

ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision

5 Feb 2021

Vision-and-Language Pretraining (VLP) has improved performance on various joint vision-and-language downstream tasks.

138
0.87 stars / hour

ResMLP: Feedforward networks for image classification with data-efficient training

7 May 2021

We present ResMLP, an architecture built entirely upon multi-layer perceptrons for image classification.

80
0.74 stars / hour

E(n) Equivariant Graph Neural Networks

19 Feb 2021

This paper introduces a new model to learn graph neural networks equivariant to rotations, translations, reflections and permutations called E(n)-Equivariant Graph Neural Networks (EGNNs).

44
0.67 stars / hour