# Unified Segmentation Framework
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 Tiny Cityscapes Instance
Other
Mask2Former is a general-purpose image segmentation model based on Transformer architecture, this version is specifically fine-tuned for instance segmentation tasks on the Cityscapes dataset
Image Segmentation
Transformers

M
facebook
67
0
Maskformer Swin Small Ade
Other
A semantic segmentation model trained on the ADE20k dataset, using a unified framework to handle instance/semantic/panoptic segmentation tasks
Image Segmentation
Transformers

M
facebook
205
2
Maskformer Swin Tiny Ade
Other
A semantic segmentation model trained on the ADE20k dataset, using a unified framework to handle instance/semantic/panoptic segmentation tasks
Image Segmentation
Transformers

M
facebook
5,196
5
Featured Recommended AI Models