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 (ViT-H, 448)

MAE (ViT-H, 448)

Reported on 10 benchmarks across 3 tasks · 1 paper · 10 SOTA

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

Computer Vision7 results

Image ClassificationoniNaturalist
Top 1 Accuracy· uses extra data· 2021-11-11
83.4
best: 85.9 (AIMv2-3B (448 res))
SOTA
Masked Autoencoders Are Scalable Vision Learners arXiv:2111.06377
Image ClassificationonPlaces205
Top 1 Accuracy· 2021-11-11
66.8
best: 69.3 (MixMIM-L)
SOTA
Masked Autoencoders Are Scalable Vision Learners arXiv:2111.06377
Image ClassificationonPlaces365-Standard
Top 1 Accuracy· uses extra data· 2021-11-11
60.3
best: 60.7 (SWAG (ViT H/14))
SOTA
Masked Autoencoders Are Scalable Vision Learners arXiv:2111.06377
Image ClassificationoniNaturalist 2019
Top-1 Accuracy· uses extra data· 2021-11-11
88.3
best: 88.5 (Hiera-H (448px))
SOTA
Masked Autoencoders Are Scalable Vision Learners arXiv:2111.06377
Domain GeneralizationonImageNet-R
Top-1 Error Rate· 2021-11-11
33.5
best: 3.9 (Model soups (BASIC-L))
SOTA
Masked Autoencoders Are Scalable Vision Learners arXiv:2111.06377
Domain GeneralizationonImageNet-A
Top-1 accuracy %· 2021-11-11
76.7
best: 94.17 (Model soups (BASIC-L))
SOTA
Masked Autoencoders Are Scalable Vision Learners arXiv:2111.06377
Domain GeneralizationonImageNet-Sketch
Top-1 accuracy· 2021-11-11
50.9
best: 77.18 (Model soups (BASIC-L))
SOTA
Masked Autoencoders Are Scalable Vision Learners arXiv:2111.06377

Methodology3 results

Domain AdaptationonImageNet-R
Top-1 Error Rate· 2021-11-11
33.5
best: 3.9 (Model soups (BASIC-L))
SOTA
Masked Autoencoders Are Scalable Vision Learners arXiv:2111.06377
Domain AdaptationonImageNet-A
Top-1 accuracy %· 2021-11-11
76.7
best: 94.17 (Model soups (BASIC-L))
SOTA
Masked Autoencoders Are Scalable Vision Learners arXiv:2111.06377
Domain AdaptationonImageNet-Sketch
Top-1 accuracy· 2021-11-11
50.9
best: 77.18 (Model soups (BASIC-L))
SOTA
Masked Autoencoders Are Scalable Vision Learners arXiv:2111.06377