Semantic Segmentation on CityScapes adapted from SYNTHIA (test val)
92.6Road IoULTIR
Evaluation results
| Method | Links | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LTIRMechanism=Adversarial Learning (AL), Source Dataset=SYNTHIA2021.03 | 92.6 | 39.4 | 46.1 | 53.2 | 79.2 | — | — | — | 1.6 | 7.5 | 78.6 | 84.4 | 52.6 | 20 | 34.8 | 14.6 | |
| Ours (multi DMLC)Mechanism=Self-Training (ST), Source Dataset=SYNTHIA2021.03 | 92.6 | 45.1 | 52.5 | 52.7 | 81.3 | 8.9 | 2.4 | 28.1 | 13 | 7.3 | 83.5 | 85 | 60.1 | 19.7 | 37.2 | 21.5 | |
| Ours (single DMLC)Mechanism=Self-Training (ST), Source Dataset=SYNTHIA2021.03 | 92.3 | 44.6 | 52.1 | 53 | 80.2 | 7.7 | 2.8 | 26.9 | 11.4 | 8.1 | 83.1 | 85.2 | 58.9 | 20.5 | 35.9 | 21 | |
| CAG-UDAMechanism=Self-Training (ST), Source Dataset=SYNTHIA2021.03 | 84.7 | 44.5 | 51.5 | 40.8 | 81.7 | 7.8 | 0 | 35.1 | 13.3 | 22.7 | 84.5 | 77.6 | 64.2 | 27.8 | 19.7 | 22.7 | |
| AdaptSegNetMechanism=Adversarial Learning (AL), Source Dataset=SYNTHIA2021.03 | 84.3 | 32.3 | 46.7 | 42.7 | 77.5 | — | — | — | 4.7 | 7 | 77.9 | 82.5 | 54.3 | 21 | 32.2 | 18.9 | |
| IntraDAMechanism=Self-Training (ST), Source Dataset=SYNTHIA2021.03 | 84.3 | 41.7 | 48.9 | 37.7 | 79.5 | 5.3 | 0.4 | 24.9 | 9.2 | 8.4 | 80 | 84.1 | 57.2 | 23 | 38.1 | 20.3 | |
| MaxSquareMechanism=Self-Training (ST), Source Dataset=SYNTHIA2021.03 | 82.9 | 41.4 | 48.2 | 40.7 | 80.3 | 10.2 | 0.8 | 25.8 | 12.8 | 18.2 | 82.5 | 82.2 | 53.1 | 18 | 31.4 | 10.4 | |
| PatchAlignMechanism=Adversarial Learning (AL), Source Dataset=SYNTHIA2021.03 | 82.4 | 31.7 | 46.5 | 38 | 78.6 | 8.7 | 0.6 | 26 | 3.9 | 11.1 | 75.5 | 84.6 | 53.5 | 21.6 | 32.6 | 19.3 | |
| PyCDAMechanism=Self-Training (ST), Source Dataset=SYNTHIA2021.03 | 75.5 | 46.7 | 53.3 | 30.9 | 83.3 | 20.8 | 0.7 | 32.7 | 27.3 | 33.5 | 84.7 | 85 | 64.1 | 25.4 | 45.2 | 21.2 | |
| CBSTMechanism=Self-Training (ST), Source Dataset=SYNTHIA2021.03 | 68 | 42.6 | 48.9 | 29.9 | 76.3 | 10.8 | 1.4 | 33.9 | 22.8 | 29.5 | 77.6 | 78.3 | 60.6 | 28.3 | 23.5 | 18.8 | |
| CRSTMechanism=Self-Training (ST), Source Dataset=SYNTHIA2021.03 | 67.7 | 43.8 | 50.1 | 32.2 | 73.9 | 10.7 | 1.6 | 37.4 | 22.2 | 31.2 | 80.8 | 80.5 | 60.8 | 29.1 | 25 | 19.4 | |
| MLSLMechanism=Self-Training (ST), Source Dataset=SYNTHIA2021.03 | 59.2 | 45.2 | 51 | 30.2 | 68.5 | 22.9 | 1 | 36.2 | 32.7 | 28.3 | 86.2 | 75.4 | 68.6 | 27.7 | 26.3 | 24.3 | |
| Source onlySource Dataset=SYNTHIA2021.03 | 55.6 | 33.5 | 38.6 | 23.8 | 74.6 | 9.2 | 0.2 | 24.4 | 6.1 | 12.1 | 74.8 | 79 | 55.3 | 19.1 | 23.3 | 13.7 |