InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning

arXiv:2403.10658v1 Announce Type: cross
Abstract: Semi-supervised learning (SSL) seeks to enhance task performance by training on both labeled and unlabeled data. Mainstream SSL image classification methods mostly optimize a loss that additively combines a supervised classification objective with a regularization term derived solely from unlabeled data. This formulation neglects the potential for interaction between labeled and unlabeled images. In this paper, we introduce InterLUDE, a new approach to enhance SSL made of two parts that each benefit from labeled-unlabeled interaction. …

abstract arxiv classification cs.cv cs.lg data image interactions loss performance regularization semi-supervised semi-supervised learning ssl supervised learning training type