Domain Adaptation On Synthia To Cityscapes
Metriken
mIoU
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | mIoU |
|---|---|
| constructing-self-motivated-pyramid | 35.9 |
| improve-cross-domain-mixed-sampling-with | 63.8 |
| context-aware-domain-adaptation-in-semantic | 40.8 |
| mic-masked-image-consistency-for-context | 67.3 |
| spatio-temporal-pixel-level-contrastive | 51.8 |
| self-supervised-augmentation-consistency-for | 52.6 |
| cross-region-domain-adaptation-for-class | 56.9 |
| sepico-semantic-guided-pixel-contrast-for | 58.1 |
| label-driven-reconstruction-for-domain | 41.1 |
| cross-domain-semantic-segmentation-via-domain | 38.1 |
| hyperbolic-active-learning-for-semantic | 78.1 |
| constructing-self-motivated-pyramid | 46.7 |
| fda-fourier-domain-adaptation-for-semantic | 40.5 |
| fredom-fairness-domain-adaptation-approach-to | 67 |
| bimal-bijective-maximum-likelihood-approach | 46.2 |
| classes-matter-a-fine-grained-adversarial | 45.2 |
| instance-adaptive-self-training-for | 49.8 |
| sepico-semantic-guided-pixel-contrast-for | 64.3 |
| iterative-loop-learning-combining-self | 76.6 |
| transferring-to-real-world-layouts-a-depth | 69.3 |
| cross-domain-semantic-segmentation-via-domain | 44.0 |
| classes-matter-a-fine-grained-adversarial | 39.5 |
| advent-adversarial-entropy-minimization-for | 41.2 |
| pipa-pixel-and-patch-wise-self-supervised | 68.2 |
| procst-boosting-semantic-segmentation-using | 61.6 |
| generalize-then-adapt-source-free-domain | 60.1 |
| transferring-and-regularizing-prediction-for-1 | 51.2 |
| domain-adaptive-semantic-segmentation-with | 55.0 |
| semantically-adaptive-image-to-image | 41.5 |
| fredom-fairness-domain-adaptation-approach-to | 59.1 |
| hrda-context-aware-high-resolution-domain | 65.8 |
| self-supervised-augmentation-consistency-for | 49.1 |
| daformer-improving-network-architectures-and | 60.9 |