Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/PromptStyler (CLIP, ViT-B/16)

PromptStyler (CLIP, ViT-B/16)

Reported on 8 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.

Methodology4 results

Domain AdaptationonPACS
Average Accuracy· 2023-07-27
97.2
best: 99 (SIMPLE+)
PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization arXiv:2307.15199
Domain AdaptationonOffice-Home
Average Accuracy· 2023-07-27
83.6
best: 90.6 (MoA (OpenCLIP, ViT-B/16))
PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization arXiv:2307.15199
Domain AdaptationonDomainNet
Average Accuracy· 2023-07-27
59.4
best: 67.4 (L2C (CLIP, ViT-L/14))
PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization arXiv:2307.15199
Domain AdaptationonVLCS
Average Accuracy· 2023-07-27
82.9
best: 85.5 (CAR-FT (CLIP, ViT-B/16))
PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization arXiv:2307.15199

Computer Vision4 results

Domain GeneralizationonPACS
Average Accuracy· 2023-07-27
97.2
best: 99 (SIMPLE+)
PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization arXiv:2307.15199
Domain GeneralizationonOffice-Home
Average Accuracy· 2023-07-27
83.6
best: 90.6 (MoA (OpenCLIP, ViT-B/16))
PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization arXiv:2307.15199
Domain GeneralizationonDomainNet
Average Accuracy· 2023-07-27
59.4
best: 67.4 (L2C (CLIP, ViT-L/14))
PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization arXiv:2307.15199
Domain GeneralizationonVLCS
Average Accuracy· 2023-07-27
82.9
best: 85.5 (CAR-FT (CLIP, ViT-B/16))
PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization arXiv:2307.15199