Masked-attention Mask Transformer for Universal Image Segmentation | VitaVision
PaperCVPR 2022 (arXiv 2021) · 2022

Masked-attention Mask Transformer for Universal Image Segmentation

Bowen ChengIshan MisraAlexander G. SchwingAlexander KirillovRohit Girdhar
arXiv 2112.01527DOIView in graph
1page built on it
0more pages cite it
1narrative
0registry papers cite it

In the Atlas

ModelPrimary source of
Mask2Former

Universal image segmentation family — MaskFormer (v1, NeurIPS 2021) reframes semantic segmentation as **mask classification**: predict a set of.

Appears in 1 narrative

NarrativeSegmentation, from Energy to Prompt

Lineage

Papers in the Atlas registry only · one dot per paper
Built upon by · 0
’16’17’18’19’20’21’22Deep Residual Learning for Image Recognition (2016)End-to-End Object Detection with Transformers (2020)Per-Pixel Classification is Not All You Need for Semantic Segmentation (2021)
Built upon by · 0