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/TWIST (ResNet-50)

TWIST (ResNet-50)

Reported on 7 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 Vision7 results

Image ClassificationonFood-101
Accuracy (%)· 2021-10-14
89.3
best: 92.9 (Bamboo (ViTB/16))
SOTA
Self-Supervised Learning by Estimating Twin Class Distributions arXiv:2110.07402
Image ClassificationonSUN397
Accuracy· 2021-10-14
67.4
best: 84.8 (µ2Net (ViT-L/16))
SOTA
Self-Supervised Learning by Estimating Twin Class Distributions arXiv:2110.07402
Image ClassificationonImageNet
ARI· 2021-10-14
30
best: 62.5 (TURTLE (CLIP + DINOv2))
SOTA
Self-Supervised Learning by Estimating Twin Class Distributions arXiv:2110.07402
Fine-Grained Image ClassificationonSUN397
Accuracy· 2021-10-14
67.4
best: 84.8 (µ2Net (ViT-L/16))
SOTA
Self-Supervised Learning by Estimating Twin Class Distributions arXiv:2110.07402
Image ClassificationonDTD
Accuracy· uses extra data· 2021-10-14
76.6
best: 90 (Linear FT(ViT-L/14))
Self-Supervised Learning by Estimating Twin Class Distributions arXiv:2110.07402
Image ClassificationonOxford-IIIT Pet Dataset
Accuracy· 2021-10-14
94.5
best: 99.6 (OmniVec2)
Self-Supervised Learning by Estimating Twin Class Distributions arXiv:2110.07402
Image ClassificationonImageNet
Accuracy (%)· 2021-10-14
40.6
best: 72.9 (TURTLE (CLIP + DINOv2))
Self-Supervised Learning by Estimating Twin Class Distributions arXiv:2110.07402