| Paper | Code | mIoU | ModelName | ReleaseDate |
|---|---|---|---|---|
| Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping | ✓ Link | 79.6 | RCF (with post-processing) | 2023-04-17 |
| Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping | ✓ Link | 76.7 | RCF (without post-processing) | 2023-04-17 |
| Segmenting Moving Objects via an Object-Centric Layered Representation | ✓ Link | 67.6 | OCLR | 2022-07-05 |
| Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion | 66.7 | GWM | 2022-05-16 | |
| Motion-inductive Self-supervised Object Discovery in Videos | 62.2 | MOD | 2022-10-01 | |
| []() | 62.0 | SIMO | ||
| TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut | 59.6 | TokenCut | 2022-09-01 | |
| The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos | ✓ Link | 57.0 | AMD | 2021-11-11 |