In vanilla task

Sorry that we don't have this experiment. This is because the training splits of dataset are different between SSFSC and FSC (see details in the Sec. On the FSC dataset, a big proportion of labeled data are used as unlabeled for sampling SSFSC tasks. Therefore, the total SSFSC training tasks contain less supervision (than FSC). We found that V A T brings limited improvement, e.g. less than "+recursive" and "+mixing" are actually While, "+mixing" has only one stage, using Q6: Require a large number of unlabeled samples.