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/SEER (RegNet10B)

SEER (RegNet10B)

Reported on 21 benchmarks across 5 tasks · 1 paper · 3 SOTA

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

Computer Vision17 results

Image ClassificationonKITTI-Dist
Top 1 Accuracy· uses extra data· 2022-02-16
78.34
SOTA
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision arXiv:2202.08360
Image ClassificationonCLEVR/Count
Top 1 Accuracy· uses extra data· 2022-02-16
89.28
SOTA
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision arXiv:2202.08360
Image ClassificationonCLEVR/Dist
Top 1 Accuracy· uses extra data· 2022-02-16
74.98
SOTA
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision arXiv:2202.08360
VideoonKinetics-700
Top-1 Accuracy· uses extra data· 2022-02-16
51.9
best: 85.9 (InternVideo2-6B)
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision arXiv:2202.08360
Image ClassificationonImageNet V2
Top 1 Accuracy· uses extra data· 2022-02-16
76.2
best: 84.63 (Model soups (BASIC-L))
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision arXiv:2202.08360
Image ClassificationonObjectNet
Top-1 Accuracy· uses extra data· 2022-02-16
60.2
best: 82.7 (CoCa)
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision arXiv:2202.08360
Image ClassificationonRESISC45
Top 1 Accuracy· uses extra data· 2022-02-16
95.61
best: 96.83 (ResNet50)
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision arXiv:2202.08360
Image ClassificationonCIFAR-10
Percentage correct· 2022-02-16
90
best: 99.5 (ViT-H/14)
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision arXiv:2202.08360
Image ClassificationonFlowers-102
Accuracy· uses extra data· 2022-02-16
96.3
best: 99.76 (CCT-14/7x2)
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision arXiv:2202.08360
Image ClassificationonCIFAR-100
Percentage correct· uses extra data· 2022-02-16
81.53
best: 96.08 (EffNet-L2 (SAM))
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision arXiv:2202.08360
Image ClassificationonMNIST
Accuracy· 2022-02-16
99.42
best: 99.87 (Branching/Merging CNN + Homogeneous Vector Capsules)
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision arXiv:2202.08360
Image ClassificationonMNIST
Percentage error· 2022-02-16
0.58
best: 0.13 (Branching/Merging CNN + Homogeneous Vector Capsules)
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision arXiv:2202.08360
Image ClassificationonSTL-10
Percentage correct· uses extra data· 2022-02-16
97.3
best: 99.64 (µ2Net+ (ViT-L/16))
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision arXiv:2202.08360
Image ClassificationonSVHN
Percentage error· uses extra data· 2022-02-16
13.6
best: 1 (E2E-M3)
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision arXiv:2202.08360
Domain GeneralizationonImageNet-R
Top-1 Error Rate· uses extra data· 2022-02-16
43.9
best: 3.9 (Model soups (BASIC-L))
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision arXiv:2202.08360
Domain GeneralizationonImageNet-A
Top-1 accuracy %· uses extra data· 2022-02-16
52.7
best: 94.17 (Model soups (BASIC-L))
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision arXiv:2202.08360
Domain GeneralizationonImageNet-Sketch
Top-1 accuracy· uses extra data· 2022-02-16
45.6
best: 77.18 (Model soups (BASIC-L))
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision arXiv:2202.08360

Methodology3 results

Domain AdaptationonImageNet-R
Top-1 Error Rate· uses extra data· 2022-02-16
43.9
best: 3.9 (Model soups (BASIC-L))
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision arXiv:2202.08360
Domain AdaptationonImageNet-A
Top-1 accuracy %· uses extra data· 2022-02-16
52.7
best: 94.17 (Model soups (BASIC-L))
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision arXiv:2202.08360
Domain AdaptationonImageNet-Sketch
Top-1 accuracy· uses extra data· 2022-02-16
45.6
best: 77.18 (Model soups (BASIC-L))
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision arXiv:2202.08360

Natural Language Processing1 result

Meme ClassificationonHateful Memes
ROC-AUC· uses extra data· 2022-02-16
0.734
best: 0.911 (RA-HMD (Qwen2-VL-7B))
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision arXiv:2202.08360