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/Model soups (ViT-G/14)

Model soups (ViT-G/14)

Reported on 10 benchmarks across 4 tasks · 1 paper · 4 SOTA

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

Computer Vision5 results

Domain GeneralizationonImageNet-R
Top-1 Error Rate· uses extra data· 2022-03-10
4.54
best: 3.9 (Model soups (BASIC-L))
SOTA
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time arXiv:2203.05482
Image ClassificationonImageNet V2
Top 1 Accuracy· uses extra data· 2022-03-10
84.22
best: 84.63 (Model soups (BASIC-L))
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time arXiv:2203.05482
Image ClassificationonObjectNet
Top-1 Accuracy· uses extra data· 2022-03-10
78.52
best: 82.7 (CoCa)
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time arXiv:2203.05482
Domain GeneralizationonImageNet-A
Top-1 accuracy %· uses extra data· 2022-03-10
92.67
best: 94.17 (Model soups (BASIC-L))
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time arXiv:2203.05482
Domain GeneralizationonImageNet-Sketch
Top-1 accuracy· uses extra data· 2022-03-10
74.24
best: 77.18 (Model soups (BASIC-L))
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time arXiv:2203.05482

Methodology4 results

Domain AdaptationonImageNet-R
Top 1 Error· uses extra data· 2022-03-10
4.54
SOTA
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time arXiv:2203.05482
Domain AdaptationonImageNet-R
Top-1 Error Rate· uses extra data· 2022-03-10
4.54
best: 3.9 (Model soups (BASIC-L))
SOTA
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time arXiv:2203.05482
Domain AdaptationonImageNet-A
Top-1 accuracy %· uses extra data· 2022-03-10
92.67
best: 94.17 (Model soups (BASIC-L))
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time arXiv:2203.05482
Domain AdaptationonImageNet-Sketch
Top-1 accuracy· uses extra data· 2022-03-10
74.24
best: 77.18 (Model soups (BASIC-L))
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time arXiv:2203.05482

Other1 result

Unsupervised Domain AdaptationonImageNet-R
Top 1 Error· uses extra data· 2022-03-10
4.54
SOTA
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time arXiv:2203.05482