Instance-Dependent Noisy Label Learning via Graphical Modelling

Open paper
Benchmark Model Rank Results
image-classification-on-red-miniimagenet-60-label-noiseInstanceGM-SS#1Accuracy: 53.21
image-classification-on-red-miniimagenet-60-label-noiseInstanceGM#3Accuracy: 47.96
learning-with-noisy-labels-on-red-miniimagenet-60-label-noiseInstanceGM-SS#1Test Accuracy: 53.21
learning-with-noisy-labels-on-red-miniimagenet-60-label-noiseInstanceGM#3Test Accuracy: 47.96
image-classification-on-red-miniimagenet-40-label-noiseInstanceGM-SS#2Accuracy: 56.37
image-classification-on-red-miniimagenet-40-label-noiseInstanceGM#4Accuracy: 52.24
image-classification-on-red-miniimagenet-80-label-noiseInstanceGM-SS#2Accuracy: 44.03
image-classification-on-red-miniimagenet-80-label-noiseInstanceGM#4Accuracy: 39.62
learning-with-noisy-labels-on-red-miniimagenet-80-label-noiseInstanceGM-SS#2Test Accuracy: 44.03
learning-with-noisy-labels-on-red-miniimagenet-80-label-noiseInstanceGM#4Test Accuracy: 39.62
image-classification-on-red-miniimagenet-20-label-noiseInstanceGM-SS#3Accuracy: 60.89
image-classification-on-red-miniimagenet-20-label-noiseInstanceGM#4Accuracy: 58.38
learning-with-noisy-labels-on-red-miniimagenet-20-label-noiseInstanceGM-SS#3Test Accuracy: 60.89
learning-with-noisy-labels-on-red-miniimagenet-20-label-noiseInstanceGM#4Test Accuracy: 58.38
learning-with-noisy-labels-on-red-miniimagenet-40-label-noiseInstanceGM-SS#3Test Accuracy: 56.37
learning-with-noisy-labels-on-red-miniimagenet-40-label-noiseInstanceGM#4Test Accuracy: 52.24
learning-with-noisy-labels-on-animalInstanceGM with ConvNeXt#11Accuracy: 84.7Network: ConvNeXtImageNet Pretrained: NO
learning-with-noisy-labels-on-animalInstanceGM#12Accuracy: 84.6Network: Vgg19-BNImageNet Pretrained: NO
learning-with-noisy-labels-on-animalInstanceGM with ResNet#15Accuracy: 82.3Network: ResNetImageNet Pretrained: NO
image-classification-on-clothing1mInstanceGM#17Accuracy: 74.40%

Rank counts only results with a code link.