Trending Research

XCiT: Cross-Covariance Image Transformers

facebookresearch/xcit 17 Jun 2021

We propose a "transposed" version of self-attention that operates across feature channels rather than tokens, where the interactions are based on the cross-covariance matrix between keys and queries.

Instance Segmentation Object Detection +2

224
2.44 stars / hour

DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning

kwai/DouZero 11 Jun 2021

Games are abstractions of the real world, where artificial agents learn to compete and cooperate with other agents.

Multi-agent Reinforcement Learning

555
2.38 stars / hour

GANs N' Roses: Stable, Controllable, Diverse Image to Image Translation (works for videos too!)

mchong6/GANsNRoses 11 Jun 2021

This adversarial loss guarantees the map is diverse -- a very wide range of anime can be produced from a single content code.

Image-to-Image Translation

475
1.50 stars / hour

SimSwap: An Efficient Framework For High Fidelity Face Swapping

neuralchen/SimSwap 11 Jun 2021

In contrast to previous approaches that either lack the ability to generalize to arbitrary identity or fail to preserve attributes like facial expression and gaze direction, our framework is capable of transferring the identity of an arbitrary source face into an arbitrary target face while preserving the attributes of the target face.

 Ranked #1 on Face Swapping on FaceForensics++ (ID retrieval metric)

Face Swapping

462
1.32 stars / hour

SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers

NVlabs/SegFormer 31 May 2021

We present SegFormer, a simple, efficient yet powerful semantic segmentation framework which unifies Transformers with lightweight multilayer perception (MLP) decoders.

Semantic Segmentation

306
1.03 stars / hour

Do Transformers Really Perform Bad for Graph Representation?

Microsoft/Graphormer 9 Jun 2021

Our key insight to utilizing Transformer in the graph is the necessity of effectively encoding the structural information of a graph into the model.

Graph Classification Graph Regression +1

187
0.92 stars / hour

EPSANet: An Efficient Pyramid Split Attention Block on Convolutional Neural Network

xmu-xiaoma666/External-Attention-pytorch 30 May 2021

Recently, it has been demonstrated that the performance of a deep convolutional neural network can be effectively improved by embedding an attention module into it.

Image Classification Instance Segmentation +2

445
0.73 stars / hour

Towards Real-World Blind Face Restoration with Generative Facial Prior

TencentARC/GFPGAN 11 Jan 2021

Blind face restoration usually relies on facial priors, such as facial geometry prior or reference prior, to restore realistic and faithful details.

Blind Face Restoration GAN inversion

116
0.67 stars / hour

LoRA: Low-Rank Adaptation of Large Language Models

microsoft/LoRA 17 Jun 2021

We propose Low-Rank Adaptation, or LoRA, which freezes the pre-trained model weights and injects trainable rank decomposition matrices into each layer of the Transformer architecture, greatly reducing the number of trainable parameters for downstream tasks.

Language Modelling

38
0.54 stars / hour

Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve Backbones

PaddlePaddle/PaddleClas 10 Mar 2021

Recently, research efforts have been concentrated on revealing how pre-trained model makes a difference in neural network performance.

Knowledge Distillation Object Detection +2

888
0.54 stars / hour