Hybrid-SF-MoE

Reported on 2 benchmarks across 2 tasks · 1 paper

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· uses extra data· 2022-06-08
52
best: 67.4 (L2C (CLIP, ViT-L/14))
Sparse Mixture-of-Experts are Domain Generalizable Learners arXiv:2206.04046

Computer Vision1 result

Domain GeneralizationonDomainNet
Average Accuracy· uses extra data· 2022-06-08
52
best: 67.4 (L2C (CLIP, ViT-L/14))
Sparse Mixture-of-Experts are Domain Generalizable Learners arXiv:2206.04046