tqdm (EVA02-CLIP-L)

Reported on 4 benchmarks across 2 tasks · 1 paper · 1 SOTA

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

Computer Vision2 results

Domain GeneralizationonGTA5-to-Cityscapes
mIoU· 2024-07-12
68.88
SOTA
Textual Query-Driven Mask Transformer for Domain Generalized Segmentation arXiv:2407.09033
Domain GeneralizationonGTA-to-Avg(Cityscapes,BDD,Mapillary)
mIoU· 2024-07-12
66.05
best: 4489 (Self-adaptation (ResNet - 101))
Textual Query-Driven Mask Transformer for Domain Generalized Segmentation arXiv:2407.09033

Methodology2 results

Domain AdaptationonGTA-to-Avg(Cityscapes,BDD,Mapillary)
mIoU· 2024-07-12
66.05
best: 4489 (Self-adaptation (ResNet - 101))
Textual Query-Driven Mask Transformer for Domain Generalized Segmentation arXiv:2407.09033
Domain AdaptationonGTA5-to-Cityscapes
mIoU· 2024-07-12
68.88
best: 74.4 (CLUDA+HRDA)
Textual Query-Driven Mask Transformer for Domain Generalized Segmentation arXiv:2407.09033