OneFormer is a universal image segmentation framework based on a Swin Transformer backbone. This variant is fine-tuned on the ADE20K dataset and can perform semantic, instance, and panoptic segmentation using a single model. It is distributed on Hugging Face for use with the Transformers library.
Oneformer Ade20k Swin Tiny sits in PulseGate's Other AI category. It focuses on performing panoptic, instance, and semantic segmentation with a single model. Oneformer Ade20k Swin Tiny is an open-source project aimed at developers. The project is open source (MIT). It runs on the web and API.
It is developed by shi-labs, and the product first shipped in 2022. The project is developed in the open on GitHub with 1.7k stars. Among its 3 catalogued features are Image Segmentation, Universal Segmentation, and Swin Transformer.
Latest indexed changes and source events
shi-labs/oneformer_ade20k_swin_tiny verified by the PulseGate indexer
Other apps tracked under the same category.
