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/MAE+DAT (ViT-H)

MAE+DAT (ViT-H)

Reported on 10 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.

Methodology5 results

Domain AdaptationonStylized-ImageNet
Top 1 Accuracy· 2022-09-16
32.77
SOTA
Enhance the Visual Representation via Discrete Adversarial Training arXiv:2209.07735
Domain AdaptationonImageNet-R
Top-1 Error Rate· 2022-09-16
34.39
best: 3.9 (Model soups (BASIC-L))
Enhance the Visual Representation via Discrete Adversarial Training arXiv:2209.07735
Domain AdaptationonImageNet-A
Top-1 accuracy %· 2022-09-16
68.92
best: 94.17 (Model soups (BASIC-L))
Enhance the Visual Representation via Discrete Adversarial Training arXiv:2209.07735
Domain AdaptationonImageNet-C
mean Corruption Error (mCE)· 2022-09-16
31.4
best: 22 (EfficientNet-L2+RPL)
Enhance the Visual Representation via Discrete Adversarial Training arXiv:2209.07735
Domain AdaptationonImageNet-Sketch
Top-1 accuracy· 2022-09-16
50.03
best: 77.18 (Model soups (BASIC-L))
Enhance the Visual Representation via Discrete Adversarial Training arXiv:2209.07735

Computer Vision5 results

Domain GeneralizationonStylized-ImageNet
Top 1 Accuracy· 2022-09-16
32.77
SOTA
Enhance the Visual Representation via Discrete Adversarial Training arXiv:2209.07735
Domain GeneralizationonImageNet-C
mean Corruption Error (mCE)· 2022-09-16
31.4
best: 28.2 (DINOv2 (ViT-g/14, frozen model, linear eval))
SOTA
Enhance the Visual Representation via Discrete Adversarial Training arXiv:2209.07735
Domain GeneralizationonImageNet-R
Top-1 Error Rate· 2022-09-16
34.39
best: 3.9 (Model soups (BASIC-L))
Enhance the Visual Representation via Discrete Adversarial Training arXiv:2209.07735
Domain GeneralizationonImageNet-A
Top-1 accuracy %· 2022-09-16
68.92
best: 94.17 (Model soups (BASIC-L))
Enhance the Visual Representation via Discrete Adversarial Training arXiv:2209.07735
Domain GeneralizationonImageNet-Sketch
Top-1 accuracy· 2022-09-16
50.03
best: 77.18 (Model soups (BASIC-L))
Enhance the Visual Representation via Discrete Adversarial Training arXiv:2209.07735