FINE + DivideMix

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

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

Computer Vision2 results

Image ClassificationonWebVision
Top 1 Accuracy· 2021-02-23
77.28
best: 78.84 (PropMix (Ours))
SOTA
FINE Samples for Learning with Noisy Labels arXiv:2102.11628
Image ClassificationonWebVision
Top 5 Accuracy· 2021-02-23
91.44
SOTA
FINE Samples for Learning with Noisy Labels arXiv:2102.11628