MIC+CSI

Reported on 6 benchmarks across 2 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology3 results

Domain AdaptationonSYNTHIA-to-Cityscapes
mIoU (19 classes)· 2024-08-05
67.4
SOTA
Cross-Domain Semantic Segmentation on Inconsistent Taxonomy using VLMs arXiv:2408.02261
Domain AdaptationonSYNTHIA-to-Cityscapes
mIoU· 2024-08-05
68.8
best: 78.1 (HALO)
Cross-Domain Semantic Segmentation on Inconsistent Taxonomy using VLMs arXiv:2408.02261
Domain AdaptationonSYNTHIA-to-Cityscapes
mIoU (13 classes)· 2024-08-05
75.9
Cross-Domain Semantic Segmentation on Inconsistent Taxonomy using VLMs arXiv:2408.02261

Other3 results

Unsupervised Domain AdaptationonSYNTHIA-to-Cityscapes
mIoU (19 classes)· 2024-08-05
67.4
SOTA
Cross-Domain Semantic Segmentation on Inconsistent Taxonomy using VLMs arXiv:2408.02261
Unsupervised Domain AdaptationonSYNTHIA-to-Cityscapes
mIoU· 2024-08-05
68.8
best: 69.3 (DCF)
Cross-Domain Semantic Segmentation on Inconsistent Taxonomy using VLMs arXiv:2408.02261
Unsupervised Domain AdaptationonSYNTHIA-to-Cityscapes
mIoU (13 classes)· 2024-08-05
75.9
Cross-Domain Semantic Segmentation on Inconsistent Taxonomy using VLMs arXiv:2408.02261