droidlet: modular, heterogenous, multi-modal agents

facebookresearch/droidlet 25 Jan 2021

In recent years, there have been significant advances in building end-to-end Machine Learning (ML) systems that learn at scale.

1.63 stars / hour

Dota 2 with Large Scale Deep Reinforcement Learning

bilibili/LastOrder-Dota2 13 Dec 2019

On April 13th, 2019, OpenAI Five became the first AI system to defeat the world champions at an esports game.

Dota 2

1.29 stars / hour

Zero-Shot Text-to-Image Generation

borisdayma/dalle-mini 24 Feb 2021

Text-to-image generation has traditionally focused on finding better modeling assumptions for training on a fixed dataset.

Zero-Shot Text-to-Image Generation

0.77 stars / hour

Contextual Transformer Networks for Visual Recognition

JDAI-CV/CoTNet 26 Jul 2021

Such design fully capitalizes on the contextual information among input keys to guide the learning of dynamic attention matrix and thus strengthens the capacity of visual representation.

Instance Segmentation Object Detection +1

0.73 stars / hour

Open-World Entity Segmentation

dvlab-research/Entity 29 Jul 2021

We introduce a new image segmentation task, termed Entity Segmentation (ES) with the aim to segment all visual entities in an image without considering semantic category labels.

Image Manipulation Semantic Segmentation

0.72 stars / hour

YOLOX: Exceeding YOLO Series in 2021

Megvii-BaseDetection/YOLOX 18 Jul 2021

In this report, we present some experienced improvements to YOLO series, forming a new high-performance detector -- YOLOX.

2D Object Detection Autonomous Driving

0.72 stars / hour

Image Cropping on Twitter: Fairness Metrics, their Limitations, and the Importance of Representation, Design, and Agency

twitter-research/image-crop-analysis 18 May 2021

However, we demonstrate that formalized fairness metrics and quantitative analysis on their own are insufficient for capturing the risk of representational harm in automatic cropping.

Fairness Image Cropping

0.52 stars / hour

CrossFormer: A Versatile Vision Transformer Based on Cross-scale Attention

cheerss/CrossFormer 31 Jul 2021

In particular, CEL blends each embedding with multiple patches of different scales, providing the model with cross-scale embeddings.

Object Detection

0.50 stars / hour

NPMs: Neural Parametric Models for 3D Deformable Shapes

pablopalafox/npms 1 Apr 2021

Parametric 3D models have enabled a wide variety of tasks in computer graphics and vision, such as modeling human bodies, faces, and hands.

Pose Transfer

0.50 stars / hour


xmu-xiaoma666/External-Attention-pytorch arXiv preprint 2021

🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

Keypoint Detection Semantic Segmentation

0.50 stars / hour