Mixup is an efficient data augmentation method which generates additional samples through respective convex combinations of original data points and labels. Although being theoretically dependent on data properties, Mixup is reported to perform well as a regularizer and calibrator contributing reliable robustness and generalization to neural network training. In this paper, inspired by Universum Learning which uses out-of-class samples to assist the target tasks, we investigate Mixup from a largely under-explored perspective -the potential to generate in-domain samples that belong to none of the target classes, that is, universum. We find that in the framework of supervised contrastive learning, universum-style Mixup produces surprisingly high-quality hard negatives, greatly relieving the need for a large batch size in contrastive learning. With these findings, we propose Universum-inspired Contrastive learning (UniCon), which incorporates Mixup strategy to generate universum data as g-negatives and pushes them apart from anchor samples of the target classes. Our approach not only improves Mixup with hard labels, but also innovates a novel measure to generate universum data. With a linear classifier on the learned representations, our method achieves 81.68% top-1 accuracy on CIFAR-100, surpassing the state of art by a significant margin of 5% with a much smaller batch size, typically, 256 in UniCon vs. 1024 in SupCon [1] using ResNet-50.
Abstract. The paper analyzes the importance of ideological and political education, the challenge that we will face in modern society. It is important to carry out ideological education in university English teaching. And we also the establishment and transformation of students' ideological thought in condition of high developing network. The knowledge form, teaching method and modes are analyzed. The implementation method of improving ideological and political education in English teaching on environment of internet plus and internet are provided. Finally, the existed problems and countermeasures to improve ideological and political education in internet era are presented. The results extend the span and force of enhancing ideological and political education in English education. The results have preferable theoretical values.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.