L2C (CLIP, ViT-B/16)

Reported on 2 benchmarks across 2 tasks

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

Methodology1 result

Domain AdaptationonDomainNet
Average Accuracy
61.2
best: 67.4 (L2C (CLIP, ViT-L/14))

Computer Vision1 result

Domain GeneralizationonDomainNet
Average Accuracy
61.2
best: 67.4 (L2C (CLIP, ViT-L/14))