Most existing approaches for dealing with noisy labels broadly fall into two categories: noise-modeling-based methods and memorization-effects-based methods.

However, these methods typically rely on strict assumptions and are limited to certain types of label noise. In this paper, we reformulate the label-noise problem from a generative-model perspective, i.e., labels are generated by gradually refining an initial random guess.

Label noise widely exists in large-scale image datasets.

Neural Information Processing Systems http://nips.cc/

The statistical information of the four individual time series datasets is shown in Table 1.

Inspired by the work by Ishida et al. (2023), we propose an estimator