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/Barlow Twins (ResNet-50)

Barlow Twins (ResNet-50)

Reported on 7 benchmarks across 3 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 Vision6 results

Image ClassificationonImageNet - 10% labeled data
Top 5 Accuracy· 2021-03-04
89.3
best: 92.6 (SimMatch + EPASS (ResNet-50))
SOTA
Barlow Twins: Self-Supervised Learning via Redundancy Reduction arXiv:2103.03230
Image ClassificationonImageNet - 1% labeled data
Top 5 Accuracy· 2021-03-04
79.2
best: 93.1 (Semi-ViT (ViT-Huge))
SOTA
Barlow Twins: Self-Supervised Learning via Redundancy Reduction arXiv:2103.03230
Semi-Supervised Image ClassificationonImageNet - 10% labeled data
Top 5 Accuracy· 2021-03-04
89.3
best: 92.6 (SimMatch + EPASS (ResNet-50))
SOTA
Barlow Twins: Self-Supervised Learning via Redundancy Reduction arXiv:2103.03230
Semi-Supervised Image ClassificationonImageNet - 1% labeled data
Top 5 Accuracy· 2021-03-04
79.2
best: 93.1 (Semi-ViT (ViT-Huge))
SOTA
Barlow Twins: Self-Supervised Learning via Redundancy Reduction arXiv:2103.03230
Image ClassificationoniNaturalist 2018
Top-1 Accuracy· 2021-03-04
46.5
best: 94.6 (OmniVec2)
Barlow Twins: Self-Supervised Learning via Redundancy Reduction arXiv:2103.03230
Image ClassificationonImageNet
Top 5 Accuracy· 2021-03-04
91
best: 99.02 (Florence-CoSwin-H)
Barlow Twins: Self-Supervised Learning via Redundancy Reduction arXiv:2103.03230

Methodology1 result

ClassificationonMHIST
Accuracy· uses extra data
84.03
best: 88.03 (MoCo-v2 (ResNet-50))