Can I read MaskFormer: Unified Segmentation Model on EtoBox?

MaskFormer: Unified Segmentation Model by Yi-Chen Chen is a document available to read on EtoBox.

What is MaskFormer: Unified Segmentation Model about?

This document proposes MaskFormer, a simple mask classification model for semantic and instance segmentation. MaskFormer predicts a set of binary masks, each associated with a single class label. This unifies semantic and instance segmentation under a single model, loss, and training procedure. MaskFormer outperforms per-pixel classification baselines, especially on datasets with many classes. It achieves state-of-the-art results on ADE20K semantic segmentation and COCO panoptic segmentation.

Author

Yi-Chen Chen

Language

EN