vix.ing · top · new · best · stats · spec

Masked-attention Mask Transformer for Universal Image Segmentation

2021/12/02 by Bowen Cheng, Ishan Misra, Cheng, Bowen +7 · 323 citations
Computer Science · #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Medical Image Segmentation Techniques

paper · pdf · doi:10.48550/arxiv.2112.01527

openalex publication_date 2021/12/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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 designing specialized architectures for each task. We present Masked-attention Mask Transformer (Mask2Former), a new architecture capable of addressing any image segmentation task (panoptic, instance or semantic). Its key components include masked attention, which extracts localized features by constraining cross-attention within predicted mask regions. In addition to reducing the research effort by at least three times, it outperforms the best specialized architectures by a significant margin on four popular datasets. Most notably, Mask2Former sets a new state-of-the-art for panoptic segmentation (57.8 PQ on COCO), instance segmentation (50.1 AP on COCO) and semantic segmentation (57.7 mIoU on ADE20K).

Citations

Cited by

Related