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/SWAG (ViT H/14)

SWAG (ViT H/14)

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

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

Computer Vision6 results

Image ClassificationonPlaces365-Standard
Top 1 Accuracy· uses extra data· 2022-01-20
60.7
SOTA
Revisiting Weakly Supervised Pre-Training of Visual Perception Models arXiv:2201.08371
Image ClassificationonImageNet
GFLOPs· 2022-01-20
1018.8
best: 1478 (InternImage-H)
SOTA
Revisiting Weakly Supervised Pre-Training of Visual Perception Models arXiv:2201.08371
Image ClassificationonImageNet V2
Top 1 Accuracy· uses extra data· 2022-01-20
81.1
best: 84.63 (Model soups (BASIC-L))
Revisiting Weakly Supervised Pre-Training of Visual Perception Models arXiv:2201.08371
Image ClassificationonObjectNet
Top-1 Accuracy· uses extra data· 2022-01-20
69.5
best: 82.7 (CoCa)
Revisiting Weakly Supervised Pre-Training of Visual Perception Models arXiv:2201.08371
Image ClassificationonCUB-200-2011
Accuracy· uses extra data· 2022-01-20
91.7
best: 92.8 (PIM)
Revisiting Weakly Supervised Pre-Training of Visual Perception Models arXiv:2201.08371
Fine-Grained Image ClassificationonCUB-200-2011
Accuracy· uses extra data· 2022-01-20
91.7
best: 92.8 (PIM)
Revisiting Weakly Supervised Pre-Training of Visual Perception Models arXiv:2201.08371