mae

[ICLR'23 Spotlight] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"

Updated Apr 11, 2023
Python

MCG-NJU / VideoMAE

Star

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

pytorch transformer action-recognition video-understanding mae video-analysis video-representation-learning self-supervised-learning masked-autoencoder vision-transformer video-transformer neurips-2022

Updated Apr 3, 2023
Python

sail-sg / Adan

Star

Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models

deep-learning optimizer pytorch artificial-intelligence resnet vit diffusion mae fairseq cuda-programming bert-model gpt2 transformer-xl timm convnext adan dreamfusion

Updated Feb 15, 2023
Python

Alpha-VL / ConvMAE

Star

ConvMAE: Masked Convolution Meets Masked Autoencoders

computer-vision backbone object-detection semantic-segmentation mae masked-image-modeling

Updated Mar 14, 2023
Python

EdisonLeeeee / Awesome-Masked-Autoencoders

Star

A collection of literature after or concurrent with Masked Autoencoder (MAE) (Kaiming He el al.).

mae self-supervised-learning masked-autoencoder

Updated Apr 5, 2023

zgcr / SimpleAICV_pytorch_training_examples_on_ImageNet_COCO_ADE20K

Star

SimpleAICV:pytorch training and testing examples on ImageNet(ILSVRC2012)/COCO2017/VOC2007+2012/CIFAR100/AED20K datasets.Include classification/object detection/distillation/contrastive learning/masked image modeling.

pytorch imagenet coco resnet vit darknet dino mae cifar100 voc ade20k retinanet fcos centernet regnet ttfnet repvgg

Updated Oct 23, 2022
Python

hustvl / MIMDet

Star

MIMDet: Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection

computer-vision transformer object-detection mae instance-segmentation vision-transformer masked-image-modeling

Updated Aug 4, 2022
Python

PaddlePaddle / PASSL

Star

PASSL包含 SimCLR，MoCo v1/v2，BYOL，CLIP，PixPro，simsiam, SwAV, BEiT，MAE 等图像自监督算法以及 Vision Transformer，DEiT，Swin Transformer，CvT，T2T-ViT，MLP-Mixer，XCiT，ConvNeXt，PVTv2 等基础视觉算法

deep-learning vit clip paddle pvt mae moco self-supervised-learning cvt simclr beit vision-transformer deit pixpro moco-v2 swav swin-transformer xcit convnext

Updated Apr 11, 2023
Python

implus / UM-MAE

Star

Official Codes for "Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality"

coco mae ade20k self-supervised-learning masked-autoencoder imagenet-classification pyramid-vision-transformer swin-transformer masked-image-modeling hierarchical-vision-transformer

Updated Dec 3, 2022
Jupyter Notebook

PaddlePaddle / PLSC

Star

Paddle Large Scale Classification Tools，supports ArcFace, CosFace, PartialFC, Data Parallel + Model Parallel. Model includes ResNet, ViT, Swin, DeiT, CaiT, FaceViT, MoCo, MAE, ConvMAE, CAE.