SHI-Labs/OneFormer
OneFormer is a transformer-based universal image segmentation model that handles semantic, instance, and panoptic segmentation tasks in a single framework.
Not currently ranked — collecting fresh signals.
star history
OneFormer is a CVPR 2023 paper and model that uses a transformer architecture to perform universal image segmentation across different task types. It unifies semantic, instance, and panoptic segmentation into a single model, trained on datasets like ADE20K, Cityscapes, and COCO. The model leverages a multi-scale transformer encoder and task-conditioned training to achieve state-of-the-art results across segmentation benchmarks.
Frequently asked
- What is SHI-Labs/OneFormer?
- OneFormer is a transformer-based universal image segmentation model that handles semantic, instance, and panoptic segmentation tasks in a single framework.
- Is OneFormer open source?
- Yes — SHI-Labs/OneFormer is open source, released under the MIT license.
- What language is OneFormer written in?
- SHI-Labs/OneFormer is primarily written in Jupyter Notebook.
- How popular is OneFormer?
- SHI-Labs/OneFormer has 1.7k stars on GitHub.
- Where can I find OneFormer?
- SHI-Labs/OneFormer is on GitHub at https://github.com/SHI-Labs/OneFormer.