shi-labs
/

oneformer_coco_swin_large

Image Segmentation

Inference Endpoints

Model card Files Files and versions Community

praeclarumjj3 commited on Jan 16, 2023

Commit

0f87c66

•

1 Parent(s): 4e19105

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -18,13 +18,13 @@ widget:
 OneFormer model trained on the COCO dataset (large-sized version, Swin backbone). It was introduced in the paper [OneFormer: One Transformer to Rule Universal Image Segmentation](https://arxiv.org/abs/2211.06220) by Jain et al. and first released in [this repository](https://github.com/SHI-Labs/OneFormer).
-![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/oneformer_teaser.png)
 ## Model description
 OneFormer is the first multi-task universal image segmentation framework. It needs to be trained only once with a single universal architecture, a single model, and on a single dataset, to outperform existing specialized models across semantic, instance, and panoptic segmentation tasks. OneFormer uses a task token to condition the model on the task in focus, making the architecture task-guided for training, and task-dynamic for inference, all with a single model.
-![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/oneformer_architecture.png)
 ## Intended uses & limitations

 OneFormer model trained on the COCO dataset (large-sized version, Swin backbone). It was introduced in the paper [OneFormer: One Transformer to Rule Universal Image Segmentation](https://arxiv.org/abs/2211.06220) by Jain et al. and first released in [this repository](https://github.com/SHI-Labs/OneFormer).
+![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/oneformer_teaser.png)
 ## Model description
 OneFormer is the first multi-task universal image segmentation framework. It needs to be trained only once with a single universal architecture, a single model, and on a single dataset, to outperform existing specialized models across semantic, instance, and panoptic segmentation tasks. OneFormer uses a task token to condition the model on the task in focus, making the architecture task-guided for training, and task-dynamic for inference, all with a single model.
+![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/oneformer_architecture.png)
 ## Intended uses & limitations