Instance Segmentation on COCO val (panoptic labels)
AP
- 2021-12-02 — Mask2Former (Swin-L, single-scale): AP 49.1
- 2022-11-10 — OneFormer (InternImage-H, emb_dim=1024, single-scale): AP 52.0
| Rank | Model | AP | Paper | Code | Year |
|---|---|---|---|---|---|
| 1 | OneFormer (InternImage-H, emb_dim=1024, single-scale) | 52.0 | OneFormer: One Transformer to Rule Universal Image Segmentation | huggingface/transformers · SHI-Labs/OneFormer · yangyucheng000/University · +1 | 2022 |
| 2 | OneFormer (DiNAT-L, single-scale) | 49.2 | OneFormer: One Transformer to Rule Universal Image Segmentation | huggingface/transformers · SHI-Labs/OneFormer · yangyucheng000/University · +1 | 2022 |
| 3 | Mask2Former (Swin-L, single-scale) | 49.1 | Masked-attention Mask Transformer for Universal Image Segmentation | huggingface/transformers · open-mmlab/mmdetection · facebookresearch/Mask2Former · +4 | 2021 |
| 4 | OneFormer (Swin-L, single-scale) | 49.0 | OneFormer: One Transformer to Rule Universal Image Segmentation | huggingface/transformers · SHI-Labs/OneFormer · yangyucheng000/University · +1 | 2022 |