"MutexMatch: Semi-Supervised Learning With Mutex-Based Consistency Regu" by Yue Duan, Zhen Zhao et al.
The core issue in semi-supervised learning (SSL) lies in how to effectively leverage unlabeled data, whereas most existing methods tend to put a great emphasis on the utilization of high-confidence samples yet seldom fully explore the usage of low-confidence samples. In this article, we aim to utilize low-confidence samples in a novel way with our proposed mutex-based consistency regularization, namely MutexMatch. Specifically, the high-confidence samples are required to exactly predict “what ...
Canadian Institute For Advanced Research Canadian Institute Advanced Research Data Models Utex Based Consistency Regularization Predictive Models
Source: uow.edu.au