Mixing Up Real Samples and Adversarial Samples for Semi-Supervised LearningDownload PDF

25 Sept 2019 (modified: 05 May 2023)ICLR 2020 Conference Withdrawn SubmissionReaders: Everyone
Abstract: Consistency regularization methods have shown great success in semi-supervised learning tasks. Most existing methods focus on either the local neighborhood or in-between neighborhood of training samples to enforce the consistency constraint. In this paper, we propose a novel generalized framework called Adversarial Mixup (AdvMixup), which unifies the local and in-between neighborhood approaches by defining a virtual data distribution along the paths between the training samples and adversarial samples. Experimental results on both synthetic data and benchmark datasets exhibit the benefits of AdvMixup on semi-supervised learning.
Original Pdf: pdf
6 Replies

Loading