From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model. (arXiv:2205.00690v2 [cs.LG] UPDATED)

Noisy labels are inevitable yet problematic in machine learning society. It
ruins the generalization power of a classifier by making the classifier be
trained to be overfitted to wrong labels. Existing methods on noisy label have
focused on modifying classifier training procedure. It results in two possible
problems. First, these methods are not applicable to a pre-trained classifier
without further access into training. Second, it is not easy to train a
classifier and remove all of negative effects from noisy …

arxiv prediction