Learning with Instance-Dependent Label Noise: A Sample Sieve Approach

Benchmark Model Rank Results
learning-with-noisy-labels-on-cifar-10n-random2CORES*#4Accuracy (mean): 94.88
learning-with-noisy-labels-on-cifar-10n-random2CORES#13Accuracy (mean): 89.91
learning-with-noisy-labels-on-cifar-10n-random3CORES*#4Accuracy (mean): 94.74
learning-with-noisy-labels-on-cifar-10n-random3CORES#13Accuracy (mean): 89.79
learning-with-noisy-labels-on-cifar-10n-aggregateCORES*#6Accuracy (mean): 95.25
learning-with-noisy-labels-on-cifar-10n-aggregateCORES#16Accuracy (mean): 91.23
learning-with-noisy-labels-on-cifar-10n-random1CORES*#6Accuracy (mean): 94.45
learning-with-noisy-labels-on-cifar-10n-random1CORES#17Accuracy (mean): 89.66
learning-with-noisy-labels-on-cifar-10n-worstCORES*#7Accuracy (mean): 91.66
learning-with-noisy-labels-on-cifar-10n-worstCORES#12Accuracy (mean): 83.60
learning-with-noisy-labels-on-cifar-100nCORES#10Accuracy (mean): 61.15
learning-with-noisy-labels-on-cifar-100nCORES*#22Accuracy (mean): 55.72
image-classification-on-clothing1mCORES2#30Accuracy: 73.24%