Semantic Segmentation on Stanford Indoor 0.2% labeled (98 samples)
44.62mIoUOurs (LF+M3L)
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Ours (LF+M3L)Input Modality=RGB, Supervision=Semi-supervised (M3L)2023.04 | 44.62 | — | — | — | — | |
| Uni-modal + CPS-SegInput Modality=RGB, Supervision=Semi-supervised (CPS-Seg)2023.04 | 42.75 | — | — | — | — | |
| LF+M3LInput Modality=Depth, Training Strategy=Semi-supervised2023.04 | 42.7 | — | — | — | — | |
| Uni-modal + MTInput Modality=RGB, Supervision=Semi-supervised (Mean Teacher)2023.04 | 41.5 | — | — | — | — | |
| Uni-modal (sup-only)Input Modality=RGB, Supervision=Supervised-only2023.04 | 39.45 | — | — | — | — | |
| Uni-modal + MTInput Modality=Depth, Training Strategy=Semi-supervised2023.04 | 37.57 | — | — | — | — | |
| Uni-modal + CPS-SegInput Modality=Depth, Training Strategy=Semi-supervised2023.04 | 36.71 | — | — | — | — | |
| Uni-modal (sup-only)Input Modality=Depth, Training Strategy=Supervised-only2023.04 | 35.24 | — | — | — | — | |
| Linear Fusiontraining_mode=supervised2023.04 | — | 33.66 | 24.61 | 46.6 | 34.96 | |
| Linear Fusion + M3Ltraining_mode=semi-supervised2023.04 | — | 44.62 | 42.7 | 49.05 | 45.46 | |
| Linear Fusion + MTtraining_mode=semi-supervised2023.04 | — | 33.99 | 23.34 | 48.54 | 35.29 | |
| TFtraining_mode=supervised2023.04 | — | 33.11 | 31.47 | 43.04 | 35.87 | |
| Uni-modaltraining_mode=supervised2023.04 | — | 39.45 | 35.24 | — | — | |
| URNtraining_mode=supervised2023.04 | — | 35.71 | 25.14 | 45.87 | 35.57 |