Improving Contrastive Learning by Visualizing Feature Transformation

Github: https://github.com/DTennant/CL-Visualizing-Feature-Transformation

Paper: https://arxiv.org/abs/2108.02982

👉 @bigdata_1

Autoregressive Image Generation using Residual Quantization

Github: https://github.com/kakaobrain/rq-vae-transformer

Pytorch: https://github.com/lucidrains/vector-quantize-pytorch

Paper: https://arxiv.org/abs/2203.01941v2

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

👉 @bigdata_1

Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data

Github: https://github.com/xinntao/Real-ESRGAN

Paper: https://arxiv.org/abs/2107.10833v1

How to Train Real-ESRGAN: https://github.com/xinntao/Real-ESRGAN/blob/master/Training.md

Colab Demo: https://colab.research.google.com/drive/1sVsoBd9AjckIXThgtZhGrHRfFI6UUYOo

👉 @bigdata_1

Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer

Github: https://github.com/williamyang1991/DualStyleGAN

Paper: https://arxiv.org/abs/2203.13248v1

Video: https://www.youtube.com/watch?v=scZTu77jixI

Project: https://www.mmlab-ntu.com/project/dualstylegan/

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

👉 @bigdata_1

AutoVideo: An Automated Video Action Recognition System

Github: https://github.com/datamllab/autovideo

Paper: https://arxiv.org/abs/2108.04212v1

👉 @bigdata_1

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

👉 @bigdata_1

Domain Aware Universal Style Transfer

Github: https://github.com/kibeom-hong/domain-aware-style-transfer

Paper: https://arxiv.org/abs/2108.04441

👉 @bigdata_1

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

👉 @bigdata_1

Contrastive Sensor Fusion

Github: https://github.com/descarteslabs/contrastive_sensor_fusion

Paper: https://arxiv.org/abs/2108.05094v1

👉 @bigdata_1

Vision-Language Transformer and Query Generation for Referring Segmentation

Github: https://github.com/henghuiding/Vision-Language-Transformer

Paper: https://arxiv.org/abs/2108.05565v1

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

👉 @bigdata_1

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

👉 @bigdata_1

Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitation

Github: https://github.com/antabangun/coex

Paper: https://arxiv.org/abs/2108.05773v1

Project: https://antabangun.github.io/projects/CoEx/#demo

👉 @bigdata_1

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

👉 @bigdata_1

Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitation

Github: https://github.com/crockwell/pixelsynth

Paper: https://arxiv.org/abs/2108.05892v1

👉 @bigdata_1

DALL·E 2

DALL·E 2 is a new AI system that can create realistic images and art from a description 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

👉 @bigdata_1

Towards Efficient and Data Agnostic Image Classification Training Pipeline for Embedded Systems

Github: https://github.com/openvinotoolkit/training_extensions

Paper: https://arxiv.org/abs/2108.07049v1

👉 @bigdata_1

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

👉 @bigdata_1

Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers

Github: https://github.com/DengPingFan/Polyp-PVT

Paper: https://arxiv.org/abs/2108.06932v1

👉 @bigdata_1

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

👉 @bigdata_1

A Unified Objective for Novel Class Discovery

Github: https://github.com/DonkeyShot21/UNO

Paper: https://arxiv.org/abs/2108.08536v2

Dataset: https://paperswithcode.com/dataset/cifar-100

👉 @bigdata_1

InsightFace: 2D and 3D Face Analysis Project

Github: https://github.com/deepinsight/insightface

Paper: https://arxiv.org/abs/2108.08191v1

Project: https://insightface.ai/projects

👉 @bigdata_1