Semantic Segmentation on Stanford Indoor (0.1% labeled (49 samples))
40.05mIoUOurs (LF+M3L)
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Ours (LF+M3L)Input Modality=RGB, Supervision=Semi-supervised (M3L)2023.04 | 40.05 | — | — | — | — | |
| LF+M3LInput Modality=Depth, Training Strategy=Semi-supervised2023.04 | 39.93 | — | — | — | — | |
| Uni-modal + CPS-SegInput Modality=RGB, Supervision=Semi-supervised (CPS-Seg)2023.04 | 37.09 | — | — | — | — | |
| Uni-modal + MTInput Modality=RGB, Supervision=Semi-supervised (Mean Teacher)2023.04 | 36.59 | — | — | — | — | |
| Uni-modal (sup-only)Input Modality=RGB, Supervision=Supervised-only2023.04 | 35.43 | — | — | — | — | |
| Uni-modal (sup-only)Input Modality=Depth, Training Strategy=Supervised-only2023.04 | 34.05 | — | — | — | — | |
| Uni-modal + CPS-SegInput Modality=Depth, Training Strategy=Semi-supervised2023.04 | 33.56 | — | — | — | — | |
| Uni-modal + MTInput Modality=Depth, Training Strategy=Semi-supervised2023.04 | 33.46 | — | — | — | — | |
| Linear Fusiontraining_mode=supervised2023.04 | — | 33.96 | 25.09 | 42.09 | 33.71 | |
| Linear Fusion + M3Ltraining_mode=semi-supervised2023.04 | — | 40.05 | 39.93 | 44.1 | 41.36 | |
| Linear Fusion + MTtraining_mode=semi-supervised2023.04 | — | 32.37 | 22.92 | 41.77 | 32.35 | |
| TFtraining_mode=supervised2023.04 | — | 29.96 | 29.98 | 40.17 | 33.37 | |
| Uni-modaltraining_mode=supervised2023.04 | — | 35.43 | 34.05 | — | — | |
| URNtraining_mode=supervised2023.04 | — | 30.56 | 25.85 | 40.17 | 32.19 |