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/Forward-T

Forward-T

Reported on 12 benchmarks across 2 tasks · 1 paper · 6 SOTA

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

Computer Vision6 results

Image ClassificationonCIFAR-10N-Random3
Accuracy (mean)· 2016-09-13
87.04
best: 96.49 (PSSCL)
SOTA
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach arXiv:1609.03683
Image ClassificationonCIFAR-10N-Aggregate
Accuracy (mean)· 2016-09-13
88.24
best: 97.39 (ProMix)
SOTA
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach arXiv:1609.03683
Image ClassificationonCIFAR-10N-Worst
Accuracy (mean)· 2016-09-13
79.79
best: 96.16 (ProMix)
SOTA
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach arXiv:1609.03683
Image ClassificationonCIFAR-10N-Random2
Accuracy (mean)· 2016-09-13
86.14
best: 96.21 (PSSCL)
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach arXiv:1609.03683
Image ClassificationonCIFAR-10N-Random1
Accuracy (mean)· 2016-09-13
86.88
best: 96.97 (ProMix)
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach arXiv:1609.03683
Image ClassificationonCIFAR-100N
Accuracy (mean)· 2016-09-13
57.01
best: 74.08 (PGDF)
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach arXiv:1609.03683

Medical6 results

Document Text ClassificationonCIFAR-10N-Random3
Accuracy (mean)· 2016-09-13
87.04
best: 96.49 (PSSCL)
SOTA
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach arXiv:1609.03683
Document Text ClassificationonCIFAR-10N-Aggregate
Accuracy (mean)· 2016-09-13
88.24
best: 97.39 (ProMix)
SOTA
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach arXiv:1609.03683
Document Text ClassificationonCIFAR-10N-Worst
Accuracy (mean)· 2016-09-13
79.79
best: 96.16 (ProMix)
SOTA
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach arXiv:1609.03683
Document Text ClassificationonCIFAR-10N-Random2
Accuracy (mean)· 2016-09-13
86.14
best: 96.21 (PSSCL)
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach arXiv:1609.03683
Document Text ClassificationonCIFAR-10N-Random1
Accuracy (mean)· 2016-09-13
86.88
best: 96.97 (ProMix)
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach arXiv:1609.03683
Document Text ClassificationonCIFAR-100N
Accuracy (mean)· 2016-09-13
57.01
best: 74.08 (PGDF)
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach arXiv:1609.03683