🤖 REGTR: End-to-end Point Cloud Correspondences with Transformers

Github: https://github.com/yewzijian/regtr

Paper: https://arxiv.org/abs/2203.14517v1

Pretrained models: https://github.com/yewzijian/RegTR/releases/download/v1/trained_models.zip

Dataset: https://paperswithcode.com/dataset/modelnet

@ai_machinelearning_big_data

⛓ Deep Automatic Natural Image Matting

Github: https://github.com/JizhiziLi/AIM

Paper: https://arxiv.org/abs/2107.07235

Pretrained models: https://drive.google.com/uc?export=download&id=16dd1FGMcsMTqR6EfD2T9mtRmPwxnY0zs

Dataset: https://paperswithcode.com/dataset/celebamask-hq

@ai_machinelearning_big_data

SuperGAT

A self-supervised graph attention network (SuperGAT), an improved graph attention model for noisy graph

Code: https://github.com/dongkwan-kim/SuperGAT

Paper: https://arxiv.org/abs/2204.04879v1

Dataset: https://paperswithcode.com/dataset/ogb

@ai_machinelearning_big_data

🗂 ObjectFolder 2.0: A Multisensory Object Dataset for Sim2Real Transfer

Github: https://github.com/rhgao/objectfolder

Paper: https://arxiv.org/abs/2204.02389v1

Project: https://ai.stanford.edu/~rhgao/objectfolder2.0/

Dataset: https://paperswithcode.com/dataset/objectfolder

@ai_machinelearning_big_data

🔥 DALL·E 2

DALL·E 2 is a new AI system that can create realistic images and art from a denoscription in natural language.

Openai: https://openai.com/dall-e-2/

Paper: https://cdn.openai.com/papers/dall-e-2.pdf

Video: https://vimeo.com/692375454

@ai_machinelearning_big_data

Vision Transformers for Single Image Dehazing

Code: https://github.com/IDKiro/DehazeFormer

Paper: https://arxiv.org/abs/2204.03883v1

Dataset: https://paperswithcode.com/dataset/rs-haze

@ai_machinelearning_big_data

🔗 Unsupervised Image-to-Image Translation with Generative Prior

A novel framework GP-UNIT, to improve the overall quality and applicability of the translation algorithm

Github: https://github.com/williamyang1991/gp-unit

Paper: https://arxiv.org/abs/2204.03641v1

Datasett: https://paperswithcode.com/dataset/celeba-hq

@ai_machinelearning_big_data

🔦 YOLOV5-ti-lite Object Detection Models

Code: https://github.com/texasinstruments/edgeai-yolov5

Paper: https://arxiv.org/abs/2204.06806v1

Dataset: https://paperswithcode.com/dataset/coco

@ArtificialIntelligencedl

✏️ Sat2lod2: A Software For Automated Lod-2 Modeling From Satellite-Derived Orthophoto And Digital Surface Model

The proposed method starts building detection results through a deep learning-based detector and vectorizes individual segments into polygons using a “three-step” polygon extraction method

Github: https://github.com/gdaosu/lod2buildingmodel

Paper: https://arxiv.org/abs/2204.04139v1

Datasett: https://drive.google.com/file/d/1rA7SRPbSYFJwOBc7IfXxBgmUroTOZIOF/view?usp=sharing

Video: https://youtu.be/Nn4OABsEOXk

@ai_machinelearning_big_data

🔎 CenterNet++ for Object Detection

Code: https://github.com/Duankaiwen/PyCenterNet

Paper: https://arxiv.org/abs/2204.08394v1

Dataset: https://paperswithcode.com/dataset/coco

✏️ Sat2lod2: A Software For Automated Lod-2 Modeling From Satellite-Derived Orthophoto And Digital Surface Model

The proposed method starts building detection results through a deep learning-based detector and vectorizes individual segments into polygons using a “three-step” polygon extraction method

Github: https://github.com/jingkang50/openood

Paper: https://arxiv.org/abs/2204.05306v1

Dataset: https://entuedu-my.sharepoint.com/:f:/g/personal/jingkang001_e_ntu_edu_sg/Eso7IDKUKQ9AoY7hm9IU2gIBMWNnWGCYPwClpH0TASRLmg?e=iEYhXO

More tutorials: https://github.com/Jingkang50/OpenOOD/wiki/Get-Started

@ai_machinelearning_big_data

Understanding Engagement from Video Screengrabs

Code: https://github.com/wanghewei16/video-engagement-analysis

Paper: https://arxiv.org/abs/2204.06454v1

The data source: https://github.com/e-drishti/wacv2016.


@ai_machinelearning_big_data

✔️ Localization Distillation for Dense Object Detection

Github: https://github.com/HikariTJU/LD

Paper: https://arxiv.org/abs/2102.12252

Datasett: https://paperswithcode.com/dataset/dota


@ai_machinelearning_big_data

OSSO: Obtaining Skeletal Shape from Outside (CVPR 2022)

Given a body shape with SMPL or STAR topology (in blue), we infer the underlying skeleton (in yellow).

Code: https://arxiv.org/abs/2204.10129v1

Paper: https://arxiv.org/abs/2204.09838v1

Dataset: https://paperswithcode.com/dataset/agora

@ArtificialIntelligencedl

🔩 Glass Segmentation with RGB-Thermal Image Pairs

Github: https://github.com/dong-huo/rgb-t-glass-segmentation

Paper: https://arxiv.org/abs/2204.05453v2

Datasett: https://drive.google.com/file/d/1ysG04qGmnZv7UaybZUuyybaJYJLUkNHX/view?usp=sharing


@ai_machinelearning_big_data

Яндекс открывает резидентскую программу по машинному обучению ML Residency.

Ее участники будут проводить исследования и эксперименты в ML, писать научные работы и посещать ведущие конференции.

Подать заявку могут как студенты и аспиранты вузов, так и опытные специалисты в профильных областях: математике, физике, компьютерных науках. Работа в проекте оплачивается.

Узнать подробнее можно здесь.

🌟 Parametric Distributionally Robust Optimization

Github: https://github.com/pmichel31415/P-DRO

Paper: https://arxiv.org/abs/2204.06340v1

Datasett: https://paperswithcode.com/dataset/celeba

@ai_machinelearning_big_data

📲 Deep-significance: Easy and Better Significance Testing for Deep Neural Networks

Github: https://github.com/Kaleidophon/deep-significance

Paper: https://arxiv.org/abs/2204.06815v1

Examples: https://github.com/Kaleidophon/deep-significance#examples

@ai_machinelearning_big_data

🤖 Transformer-Rankers

Transformer-rankers is a library to conduct ranking experiments with transformers.


Code: https://github.com/Guzpenha/transformer_rankers

Paper: https://arxiv.org/abs/2204.10558v1

Colab: https://colab.research.google.com/drive/1wGmaO3emC7Sg-tA7nGehIQ2vjOLN9S5e?usp=sharing

👁 An Extendable, Efficient and Effective Transformer-based Object Detector

Github: https://github.com/naver-ai/vidt

Paper: https://arxiv.org/abs/2204.07962v1

Dataset: https://paperswithcode.com/dataset/coco

@ai_machinelearning_big_data

🌐 DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings


Code: https://github.com/voidism/diffcse

Paper: https://arxiv.org/abs/2204.10298v1

Dataset: https://paperswithcode.com/dataset/sst

@ai_machinelearning_big_data