Trending Research

Diffusion Models Beat GANs on Image Synthesis

openai/guided-diffusion 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.

Image Generation

226
3.68 stars / hour

PAFNet: An Efficient Anchor-Free Object Detector Guidance

PaddlePaddle/PaddleDetection 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)

Object Detection

3,597
1.45 stars / hour

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

capitalone/DataProfiler 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.

Named Entity Recognition

307
1.37 stars / hour

Adversarial Open Domain Adaption for Sketch-to-Photo Synthesis

Mukosame/Anime2Sketch 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.

Domain Adaptation Image-to-Image Translation +1

939
1.06 stars / hour
103
1.06 stars / hour

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

facebookresearch/LeViT 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.

General Classification Image Classification

213
0.90 stars / hour

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

dandelin/vilt 5 Feb 2021

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

Image-to-Text Retrieval Text-to-Image Retrieval +2

138
0.87 stars / hour

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

lucidrains/res-mlp-pytorch 7 May 2021

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

Data Augmentation General Classification +1

80
0.74 stars / hour

E(n) Equivariant Graph Neural Networks

vgsatorras/egnn 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).

Representation Learning

44
0.67 stars / hour