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/BiT-M (ResNet)

BiT-M (ResNet)

Reported on 8 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 Vision8 results

Image ClassificationonOxford 102 Flowers
Top-1 Error Rate· uses extra data· 2019-12-24
0.7
best: 0.37 (BiT-L (ResNet))
SOTA
Big Transfer (BiT): General Visual Representation Learning arXiv:1912.11370
Fine-Grained Image ClassificationonOxford 102 Flowers
Top-1 Error Rate· uses extra data· 2019-12-24
0.7
best: 0.37 (BiT-L (ResNet))
SOTA
Big Transfer (BiT): General Visual Representation Learning arXiv:1912.11370
Image ClassificationonCIFAR-10
Percentage correct· 2019-12-24
98.91
best: 99.5 (ViT-H/14)
Big Transfer (BiT): General Visual Representation Learning arXiv:1912.11370
Image ClassificationonFlowers-102
Accuracy· uses extra data· 2019-12-24
99.3
best: 99.76 (CCT-14/7x2)
Big Transfer (BiT): General Visual Representation Learning arXiv:1912.11370
Image ClassificationonObjectNet (Bounding Box)
Top 5 Accuracy· uses extra data· 2019-12-24
76
best: 85.1 (BiT-L (ResNet))
Big Transfer (BiT): General Visual Representation Learning arXiv:1912.11370
Image ClassificationonCIFAR-100
Percentage correct· uses extra data· 2019-12-24
92.17
best: 96.08 (EffNet-L2 (SAM))
Big Transfer (BiT): General Visual Representation Learning arXiv:1912.11370
Image ClassificationonOxford-IIIT Pets
Accuracy· 2019-12-24
94.47
best: 97.1 (EffNet-L2 (SAM))
Big Transfer (BiT): General Visual Representation Learning arXiv:1912.11370
Fine-Grained Image ClassificationonOxford-IIIT Pets
Accuracy· 2019-12-24
94.47
best: 97.1 (EffNet-L2 (SAM))
Big Transfer (BiT): General Visual Representation Learning arXiv:1912.11370