The transition matrix, denoting the transition relationship from clean labels to noisy labels, is essential to buildstatistically consistentclassifiers in label-noise learning.

Subseasonal forecasting of the weather two to six weeks in advance is critical for resource allocation and advance disaster notice but poses many challenges for the forecasting community.

Concretely, we propose a coarse-to-fine framework, which starts with acoarsedomain discovery step via progressive domain discriminator training.