mae 开源项目推荐（165 个）

open-mmlab /mmpretrain

OpenMMPLab预培训收件箱和基准

open-mmlab /mmselfsup

OpenMMLab自我监督学习工作表和基准

ViTAE-Transformer /ViTPose

[NeurIPS ' 22]“ViTPose：用于人体姿势估计的简单视觉Transformer基线”和[TPAMI ' 23]“ViTPose++：用于通用身体姿势估计的视觉Transformer”的官方回购

MCG-NJU /VideoMAE

[NeurIPS 2022聚焦] VideoMAE：屏蔽自动编码器是自我监督视频预训练的数据高效学习者

vturrisi /solo-learn

solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning

keyu-tian /SparK

[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"

EdisonLeeeee /Awesome-Masked-Autoencoders

这是一集在与蒙面自编码器（MAE）之后或同时进行的文献集（Kaiming He el al.）。

sail-sg /Adan

Adan：用于更快优化深度模型的自适应 Nesterov 动量算法

Alpha-VL /ConvMAE

ConvMAE: Masked Convolution Meets Masked Autoencoders

Lupin1998 /Awesome-MIM

[Survey] Masked Modeling for Self-supervised Representation Learning on Vision and Beyond (https://arxiv.org/abs/2401.00897)

lartpang /PySODEvalToolkit

PySODEvalToolkit: A Python-based Evaluation Toolbox for Salient Object Detection and Camouflaged Object Detection

hustvl /MIMDet

[ICCV 2023] You Only Look at One Partial Sequence

ywyue /FiT3D

[ECCV 2024] Improving 2D Feature Representations by 3D-Aware Fine-Tuning

PaddlePaddle /PASSL

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

megvii-research /RevCol

Official Code of Paper "Reversible Column Networks" "RevColv2"

Event-AHU /Medical_Image_Analysis

Foundation models based medical image analysis

Mountchicken /Union14M

[ICCV 2023] Code base for Revisiting Scene Text Recognition: A Data Perspective

wangtz19 /NetMamba

Efficient Network Traffic Classification via Pre-training Unidirectional Mamba

PaddlePaddle /PLSC

Paddle 大型分类工具，支持 ArcFace、CosFace、PartialFC、Data Parallel + Model Parallel。模型包括ResNet、ViT、Swin、DeiT、CaiT、FaceViT、MoCo、MAE、ConvMAE、CAE。

Berry-Wu /Visualization

visualization：filter、feature map、attention map、image-mask、grad-cam、human keypoint、guided-backpro