Mask2Former

Papers using or citing this model 1

• Masked-attention Mask Transformer for Universal Image Segmentation 4.7K citations · 2021 · arXiv (Cornell University) · arXiv

  Image segmentation is about grouping pixels with different semantics, e.g., category or instance membership, where each choice of semantics defines a task. While only the semantics of each task differ, current research focuses on...