# Multi-scale Deformable Attention

Mask2Former is a Transformer-based general-purpose image segmentation model that unifies instance, semantic, and panoptic segmentation tasks.

Mask2Former is a unified image segmentation model based on Transformer, capable of handling instance segmentation, semantic segmentation, and panoptic segmentation tasks.

Mask2Former is a universal image segmentation model capable of handling instance segmentation, semantic segmentation, and panoptic segmentation tasks by predicting a set of masks and their corresponding labels.