Skip to content

Masked Autoencoders ViT-H

Facebook AI ResearchSemantic segmentationImage classificationImage generationOpen weights

Developed by Facebook AI Research in 2021, Masked Autoencoders ViT-H is a semantic segmentation model with 632000000.0 parameters with openly available weights.

About Masked Autoencoders ViT-H

This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision. Our MAE approach is simple: we mask random patches of the input image and reconstruct the missing pixels. It is based on two core designs. Firs

Details

Provider
Facebook AI Research
Task
Semantic segmentation,Image classification,Image generation
Parameters
632000000.0
Released
2021-11-11
Open weights
Yes
View model source

Explore

FAQ