Transductive zero-shot learning (TZSL) has been proposed to address the domain shift problem by leveraging additional unlabeled unseen data to enhance the generalization ability from seen classes to unseen target classes. Existing TZSL methods …
In this paper, we propose a novel method to address the challenge of learning deep neural network models in the presence of open-set noisy labels, which include mislabeled samples from out-of-distribution categories. Previous methods relied on the …
Most existing methods that cope with noisy labels usually assume that the class-wise data distributions are well balanced. They are difficult to deal with the practical scenarios where training samples have imbalanced distributions, since they are …
Open-set semi-supervised learning~(open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data. While the mainstream technique seeks to completely filter out the OOD …