Unsupervised Object Segmentation On Segtrack
평가 지표
mIoU
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | mIoU | Paper Title | Repository |
|---|---|---|---|
| SIMO | 62.0 | - | - |
| MOD | 62.2 | Motion-inductive Self-supervised Object Discovery in Videos | - |
| OCLR | 67.6 | Segmenting Moving Objects via an Object-Centric Layered Representation | |
| RCF (without post-processing) | 76.7 | Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping | |
| TokenCut | 59.6 | TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut | - |
| GWM | 66.7 | Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion | - |
| AMD | 57.0 | The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos | |
| RCF (with post-processing) | 79.6 | Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping |
0 of 8 row(s) selected.