MCDA

Reported on 6 benchmarks across 2 tasks · 1 paper · 3 SOTA

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

Computer Vision3 results

Multi-target Domain AdaptationonOffice-31
Accuracy· 2023-02-03
89.6
SOTA
Class Overwhelms: Mutual Conditional Blended-Target Domain Adaptation arXiv:2302.01516
Multi-target Domain AdaptationonOffice-Home
Accuracy· 2023-02-03
71.1
SOTA
Class Overwhelms: Mutual Conditional Blended-Target Domain Adaptation arXiv:2302.01516
Multi-target Domain AdaptationonDomainNet
Accuracy· 2023-02-03
34.5
SOTA
Class Overwhelms: Mutual Conditional Blended-Target Domain Adaptation arXiv:2302.01516

Methodology3 results

Domain AdaptationonDomainNet
Average Accuracy· 2023-02-03
34.5
best: 67.4 (L2C (CLIP, ViT-L/14))
Class Overwhelms: Mutual Conditional Blended-Target Domain Adaptation arXiv:2302.01516
Domain AdaptationonOffice-Home
Average Accuracy· 2023-02-03
71.1
best: 90.6 (MoA (OpenCLIP, ViT-B/16))
Class Overwhelms: Mutual Conditional Blended-Target Domain Adaptation arXiv:2302.01516
Domain AdaptationonOffice-31
Average Accuracy· 2023-02-03
89.6
best: 96 (FFTAT)
Class Overwhelms: Mutual Conditional Blended-Target Domain Adaptation arXiv:2302.01516