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/CAR-FT (CLIP, ViT-B/16)

CAR-FT (CLIP, ViT-B/16)

Reported on 10 benchmarks across 2 tasks · 1 paper · 6 SOTA

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

Methodology5 results

Domain AdaptationonOffice-Home
Average Accuracy· 2022-11-29
85.7
best: 90.6 (MoA (OpenCLIP, ViT-B/16))
SOTA
Context-Aware Robust Fine-Tuning arXiv:2211.16175
Domain AdaptationonDomainNet
Average Accuracy· uses extra data· 2022-11-29
62.5
best: 67.4 (L2C (CLIP, ViT-L/14))
SOTA
Context-Aware Robust Fine-Tuning arXiv:2211.16175
Domain AdaptationonVLCS
Average Accuracy· 2022-11-29
85.5
SOTA
Context-Aware Robust Fine-Tuning arXiv:2211.16175
Domain AdaptationonPACS
Average Accuracy· 2022-11-29
96.8
best: 99 (SIMPLE+)
Context-Aware Robust Fine-Tuning arXiv:2211.16175
Domain AdaptationonTerraIncognita
Average Accuracy· 2022-11-29
61.9
best: 69.6 (UniDG + CORAL + ConvNeXt-B)
Context-Aware Robust Fine-Tuning arXiv:2211.16175

Computer Vision5 results

Domain GeneralizationonOffice-Home
Average Accuracy· 2022-11-29
85.7
best: 90.6 (MoA (OpenCLIP, ViT-B/16))
SOTA
Context-Aware Robust Fine-Tuning arXiv:2211.16175
Domain GeneralizationonDomainNet
Average Accuracy· uses extra data· 2022-11-29
62.5
best: 67.4 (L2C (CLIP, ViT-L/14))
SOTA
Context-Aware Robust Fine-Tuning arXiv:2211.16175
Domain GeneralizationonVLCS
Average Accuracy· 2022-11-29
85.5
SOTA
Context-Aware Robust Fine-Tuning arXiv:2211.16175
Domain GeneralizationonPACS
Average Accuracy· 2022-11-29
96.8
best: 99 (SIMPLE+)
Context-Aware Robust Fine-Tuning arXiv:2211.16175
Domain GeneralizationonTerraIncognita
Average Accuracy· 2022-11-29
61.9
best: 69.6 (UniDG + CORAL + ConvNeXt-B)
Context-Aware Robust Fine-Tuning arXiv:2211.16175