no code implementations • 3 May 2023 • Wanli Li, Tieyun Qian
However, current generative models lack the optimization process of model generalization on different tasks during training, and thus have limited generalization capability.
1 code implementation • 2 Dec 2021 • Wanli Li, Tieyun Qian
Specifically, we first let the teachers correspond to the multiple models and select the samples in the intersection set of the last iteration in SSRE methods to augment labeled data as usual.
no code implementations • 22 Oct 2020 • Wanli Li, Tieyun Qian
To tackle this limitation, we propose to build the connection between the unlabeled data and the labeled ones rather than directly mapping the unlabeled samples to the classes.