SOTAVerified

Masked-attention Mask Transformer for Universal Image Segmentation

2021-12-02CVPR 2022Code Available2· sign in to hype

Bowen Cheng, Ishan Misra, Alexander G. Schwing, Alexander Kirillov, Rohit Girdhar

Code Available — Be the first to reproduce this paper.

Reproduce

Code

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).

Tasks

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
WildScenesMask2Former (ResNet-50)mIoU43.71Unverified
WildScenesMask2Former (Swin-L)mIoU47.85Unverified

Reproductions