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/MAWS (ViT-2B)

MAWS (ViT-2B)

Reported on 16 benchmarks across 3 tasks · 1 paper · 7 SOTA

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

Computer Vision16 results

Image ClassificationoniNaturalist 2018 - 1-shot
Top 1 Accuracy· uses extra data· 2023-03-23
35.5
SOTA
The effectiveness of MAE pre-pretraining for billion-scale pretraining arXiv:2303.13496
Image ClassificationoniNaturalist 2018 - 5-shot
Top 1 Accuracy· uses extra data· 2023-03-23
72.8
SOTA
The effectiveness of MAE pre-pretraining for billion-scale pretraining arXiv:2303.13496
Image ClassificationoniNaturalist 2018 - 10-shot
Top 1 Accuracy· uses extra data· 2023-03-23
80.3
SOTA
The effectiveness of MAE pre-pretraining for billion-scale pretraining arXiv:2303.13496
Few-Shot Image ClassificationoniNaturalist 2018 - 1-shot
Top 1 Accuracy· uses extra data· 2023-03-23
35.5
SOTA
The effectiveness of MAE pre-pretraining for billion-scale pretraining arXiv:2303.13496
Few-Shot Image ClassificationoniNaturalist 2018 - 5-shot
Top 1 Accuracy· uses extra data· 2023-03-23
72.8
SOTA
The effectiveness of MAE pre-pretraining for billion-scale pretraining arXiv:2303.13496
Few-Shot Image ClassificationoniNaturalist 2018 - 10-shot
Top 1 Accuracy· uses extra data· 2023-03-23
80.3
SOTA
The effectiveness of MAE pre-pretraining for billion-scale pretraining arXiv:2303.13496
Zero-Shot Transfer Image ClassificationonFood-101
Top 1 Accuracy· 2023-03-23
96.2
SOTA
The effectiveness of MAE pre-pretraining for billion-scale pretraining arXiv:2303.13496
Image ClassificationonImageNet V2
Top 1 Accuracy· uses extra data· 2023-03-23
83
best: 84.63 (Model soups (BASIC-L))
The effectiveness of MAE pre-pretraining for billion-scale pretraining arXiv:2303.13496
Image ClassificationonObjectNet
Top-1 Accuracy· uses extra data· 2023-03-23
75.8
best: 82.7 (CoCa)
The effectiveness of MAE pre-pretraining for billion-scale pretraining arXiv:2303.13496
Image ClassificationonImageNet - 5-shot
Top 1 Accuracy· uses extra data· 2023-03-23
81.5
best: 82.78 (ViT-MoE-15B (Every-2))
The effectiveness of MAE pre-pretraining for billion-scale pretraining arXiv:2303.13496
Image ClassificationonImageNet - 10-shot
Top 1 Accuracy· uses extra data· 2023-03-23
83.7
best: 84.6 (MAWS (ViT-6.5B))
The effectiveness of MAE pre-pretraining for billion-scale pretraining arXiv:2303.13496
Image ClassificationonImageNet - 1-shot
Top 1 Accuracy· uses extra data· 2023-03-23
62.1
best: 68.66 (ViT-MoE-15B (Every-2))
The effectiveness of MAE pre-pretraining for billion-scale pretraining arXiv:2303.13496
Few-Shot Image ClassificationonImageNet - 5-shot
Top 1 Accuracy· uses extra data· 2023-03-23
81.5
best: 82.78 (ViT-MoE-15B (Every-2))
The effectiveness of MAE pre-pretraining for billion-scale pretraining arXiv:2303.13496
Few-Shot Image ClassificationonImageNet - 10-shot
Top 1 Accuracy· uses extra data· 2023-03-23
83.7
best: 84.6 (MAWS (ViT-6.5B))
The effectiveness of MAE pre-pretraining for billion-scale pretraining arXiv:2303.13496
Few-Shot Image ClassificationonImageNet - 1-shot
Top 1 Accuracy· uses extra data· 2023-03-23
62.1
best: 68.66 (ViT-MoE-15B (Every-2))
The effectiveness of MAE pre-pretraining for billion-scale pretraining arXiv:2303.13496
Zero-Shot Transfer Image ClassificationonImageNet
Accuracy (Private)· 2023-03-23
82.1
best: 88.5 (M2-Encoder)
The effectiveness of MAE pre-pretraining for billion-scale pretraining arXiv:2303.13496