VLTSeg (EVA02-CLIP-L)

Reported on 2 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 Vision1 result

Domain GeneralizationonGTA5-to-Cityscapes
mIoU· 2023-12-04
65.6
best: 68.88 (tqdm (EVA02-CLIP-L))
SOTA
Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learning arXiv:2312.02021

Methodology1 result

Domain AdaptationonGTA5-to-Cityscapes
mIoU· 2023-12-04
65.6
best: 74.4 (CLUDA+HRDA)
Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learning arXiv:2312.02021