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/Peer Loss

Peer Loss

Reported on 12 benchmarks across 2 tasks · 1 paper

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-Random2
Accuracy (mean)· 2019-10-08
88.76
best: 96.21 (PSSCL)
Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates arXiv:1910.03231
Image ClassificationonCIFAR-10N-Random3
Accuracy (mean)· 2019-10-08
88.57
best: 96.49 (PSSCL)
Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates arXiv:1910.03231
Image ClassificationonCIFAR-10N-Aggregate
Accuracy (mean)· 2019-10-08
90.75
best: 97.39 (ProMix)
Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates arXiv:1910.03231
Image ClassificationonCIFAR-10N-Random1
Accuracy (mean)· 2019-10-08
89.06
best: 96.97 (ProMix)
Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates arXiv:1910.03231
Image ClassificationonCIFAR-100N
Accuracy (mean)· 2019-10-08
57.59
best: 74.08 (PGDF)
Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates arXiv:1910.03231
Image ClassificationonCIFAR-10N-Worst
Accuracy (mean)· 2019-10-08
82.53
best: 96.16 (ProMix)
Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates arXiv:1910.03231

Medical6 results

Document Text ClassificationonCIFAR-10N-Random2
Accuracy (mean)· 2019-10-08
88.76
best: 96.21 (PSSCL)
Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates arXiv:1910.03231
Document Text ClassificationonCIFAR-10N-Random3
Accuracy (mean)· 2019-10-08
88.57
best: 96.49 (PSSCL)
Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates arXiv:1910.03231
Document Text ClassificationonCIFAR-10N-Aggregate
Accuracy (mean)· 2019-10-08
90.75
best: 97.39 (ProMix)
Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates arXiv:1910.03231
Document Text ClassificationonCIFAR-10N-Random1
Accuracy (mean)· 2019-10-08
89.06
best: 96.97 (ProMix)
Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates arXiv:1910.03231
Document Text ClassificationonCIFAR-100N
Accuracy (mean)· 2019-10-08
57.59
best: 74.08 (PGDF)
Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates arXiv:1910.03231
Document Text ClassificationonCIFAR-10N-Worst
Accuracy (mean)· 2019-10-08
82.53
best: 96.16 (ProMix)
Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates arXiv:1910.03231