| The Missing Point in Vision Transformers for Universal Image Segmentation | ✓ Link | 49.0 | | 49.0 | ViT-P (OneFormer, ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained) | 2025-05-26 |
| OneFormer: One Transformer to Rule Universal Image Segmentation | ✓ Link | 48.7 | | | OneFormer (ConvNeXt-L, single-scale, Mapillary-Pretrained) | 2022-11-10 |
| A Simple Framework for Open-Vocabulary Segmentation and Detection | ✓ Link | 48.5 | | | OpenSeeD( SwinL, single-scale) | 2023-03-14 |
| AutoFocusFormer: Image Segmentation off the Grid | ✓ Link | 46.2 | 74.2 | | AFF-Base (single-scale, point-based Mask2Former) | 2023-04-24 |
| OneFormer: One Transformer to Rule Universal Image Segmentation | ✓ Link | 45.6 | | | OneFormer (DiNAT-L, single-scale) | 2022-11-10 |
| OneFormer: One Transformer to Rule Universal Image Segmentation | ✓ Link | 45.6 | | | OneFormer (Swin-L, single-scale) | 2022-11-10 |
| Dilated Neighborhood Attention Transformer | ✓ Link | 45.1 | 72.6 | | DiNAT-L (single-scale, Mask2Former) | 2022-09-29 |
| AutoFocusFormer: Image Segmentation off the Grid | ✓ Link | 44.0 | 72.8 | | AFF-Small (single-scale, point-based Mask2Former) | 2023-04-24 |
| Masked-attention Mask Transformer for Universal Image Segmentation | ✓ Link | 43.7 | | | Mask2Former (Swin-L, single-scale) | 2021-12-02 |
| Masked-attention Mask Transformer for Universal Image Segmentation | ✓ Link | 42 | | | Mask2Former (Swin-B) | 2021-12-02 |
| Masked-attention Mask Transformer for Universal Image Segmentation | ✓ Link | 41.8 | | | Mask2Former (Swin-S) | 2021-12-02 |
| Recurrent Generic Contour-based Instance Segmentation with Progressive Learning | ✓ Link | 40.2 | | | PolySnake | 2023-01-21 |
| Masked-attention Mask Transformer for Universal Image Segmentation | ✓ Link | 39.7 | | | Mask2Former (Swin-T) | 2021-12-02 |
| Masked-attention Mask Transformer for Universal Image Segmentation | ✓ Link | 38.5 | | | Mask2Former (ResNet-101) | 2021-12-02 |
| Masked-attention Mask Transformer for Universal Image Segmentation | ✓ Link | 37.4 | | | Mask2Former (ResNet-50) | 2021-12-02 |
| Geometry-Aware Instance Segmentation with Disparity Maps | ✓ Link | 37.1 | | | GAIS-Net | 2020-06-14 |
| PointRend: Image Segmentation as Rendering | ✓ Link | 35.8 | | | PointRend | 2019-12-17 |