DADG (ResNet-18)

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

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

Methodology2 results

Domain AdaptationonVLCS
Average Accuracy· 2020-11-01
78.21
best: 85.5 (CAR-FT (CLIP, ViT-B/16))
SOTA
Discriminative Adversarial Domain Generalization with Meta-learning based Cross-domain Validation arXiv:2011.00444
Domain AdaptationonOffice-Home
Average Accuracy· 2020-11-01
62.22
best: 90.6 (MoA (OpenCLIP, ViT-B/16))
Discriminative Adversarial Domain Generalization with Meta-learning based Cross-domain Validation arXiv:2011.00444

Computer Vision2 results

Domain GeneralizationonVLCS
Average Accuracy· 2020-11-01
78.21
best: 85.5 (CAR-FT (CLIP, ViT-B/16))
SOTA
Discriminative Adversarial Domain Generalization with Meta-learning based Cross-domain Validation arXiv:2011.00444
Domain GeneralizationonOffice-Home
Average Accuracy· 2020-11-01
62.22
best: 90.6 (MoA (OpenCLIP, ViT-B/16))
Discriminative Adversarial Domain Generalization with Meta-learning based Cross-domain Validation arXiv:2011.00444