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/µ2Net (ViT-L/16)

µ2Net (ViT-L/16)

Reported on 11 benchmarks across 2 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 Vision11 results

Image ClassificationonKMNIST
Accuracy· 2022-05-25
98.68
SOTA
An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems arXiv:2205.12755
Image ClassificationonEMNIST-Digits
Accuracy (%)· 2022-05-25
99.82
SOTA
An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems arXiv:2205.12755
Image ClassificationonSUN397
Accuracy· 2022-05-25
84.8
SOTA
An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems arXiv:2205.12755
Fine-Grained Image ClassificationonSUN397
Accuracy· 2022-05-25
84.8
SOTA
An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems arXiv:2205.12755
Image ClassificationonDTD
Accuracy· uses extra data· 2022-05-25
81
best: 90 (Linear FT(ViT-L/14))
An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems arXiv:2205.12755
Image ClassificationonCIFAR-10
Percentage correct· uses extra data· 2022-05-25
99.49
best: 99.5 (ViT-H/14)
An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems arXiv:2205.12755
Image ClassificationonCIFAR-100
Percentage correct· uses extra data· 2022-05-25
94.95
best: 96.08 (EffNet-L2 (SAM))
An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems arXiv:2205.12755
Image ClassificationonMNIST
Accuracy· 2022-05-25
99.75
best: 99.87 (Branching/Merging CNN + Homogeneous Vector Capsules)
An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems arXiv:2205.12755
Image ClassificationonEuroSAT
Accuracy (%)· 2022-05-25
99.2
best: 99.41 (DeepEnsembling)
An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems arXiv:2205.12755
Image ClassificationonOxford-IIIT Pets
Accuracy· 2022-05-25
95.3
best: 97.1 (EffNet-L2 (SAM))
An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems arXiv:2205.12755
Fine-Grained Image ClassificationonOxford-IIIT Pets
Accuracy· 2022-05-25
95.3
best: 97.1 (EffNet-L2 (SAM))
An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems arXiv:2205.12755