Download
Mask2Former is a unified segmentation architecture that handles semantic, instance, and panoptic segmentation with one model and one training recipe. Its core idea is to cast segmentation as mask classification: a transformer decoder predicts a set of mask queries, each with an associated class score, eliminating the need for task-specific heads. A pixel decoder fuses multi-scale features and feeds masked attention in the transformer so each query focuses computation on its current spatial support. This leads to accurate masks with sharp boundaries and strong small-object performance while remaining efficient on high-resolution inputs. The project provides extensive configurations and pretrained models across popular benchmarks like COCO, ADE20K, and Cityscapes. Built on top of Detectron2, it includes training scripts, inference tools, and visualization utilities that make experimentation straightforward.
Features
- Single architecture for semantic, instance, and panoptic segmentation
- Mask-classification formulation with a transformer decoder over queries
- Pixel decoder plus masked attention for focused, efficient computation
- Multi-scale feature fusion for robust small-object and boundary accuracy
- Comprehensive configs and pretrained models on standard datasets
- Detectron2-based training, inference, and visualization tools
Project Samples
