AIbase
EN
Model Selection
Tags
Masked Attention

# Masked Attention

Video Mask2former Swin Tiny Youtubevis 2021 Instance
MIT
A tiny video instance segmentation model trained on the YouTubeVIS-2021 dataset, utilizing a Swin Transformer backbone network
Image Segmentation Transformers
V
shivalikasingh
22
2
Mask2former Swin Base IN21k Cityscapes Panoptic
Other
Mask2Former is a general-purpose image segmentation model based on Transformer architecture, capable of handling instance segmentation, semantic segmentation, and panoptic segmentation tasks.
Image Segmentation Transformers
M
facebook
140
0
Mask2former Swin Small Cityscapes Panoptic
Other
A compact Mask2Former model based on Swin backbone network, optimized for panoptic segmentation tasks on the Cityscapes dataset
Image Segmentation Transformers
M
facebook
568
0
Mask2former Swin Small Coco Panoptic
Other
A small-scale version of Mask2Former based on Swin backbone network, optimized for panoptic segmentation tasks on the COCO dataset
Image Segmentation Transformers
M
facebook
240
1
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase