IDEA-Research/MaskDINO
A unified transformer-based framework for object detection, instance segmentation, semantic segmentation, and panoptic segmentation tasks.
Not currently ranked — collecting fresh signals.
star history
MaskDINO extends the DINO detector with a mask prediction head to handle both detection and segmentation tasks within a single transformer architecture. The model unifies multiple computer vision tasks including instance segmentation, semantic segmentation, and panoptic segmentation through a shared framework. It achieves state-of-the-art results on COCO and ADE20K benchmarks. The implementation includes training scripts, evaluation tools, and pretrained models for downstream use.
Frequently asked
- What is IDEA-Research/MaskDINO?
- A unified transformer-based framework for object detection, instance segmentation, semantic segmentation, and panoptic segmentation tasks.
- Is MaskDINO open source?
- Yes — IDEA-Research/MaskDINO is open source, released under the Apache-2.0 license.
- What language is MaskDINO written in?
- IDEA-Research/MaskDINO is primarily written in Python.
- How popular is MaskDINO?
- IDEA-Research/MaskDINO has 1.5k stars on GitHub.
- Where can I find MaskDINO?
- IDEA-Research/MaskDINO is on GitHub at https://github.com/IDEA-Research/MaskDINO.