ReRankMatch: Semi-Supervised Learning with Semantics-Oriented Similarity Representation

02/12/2021

∙

by   Trung Quang Tran, et al.

∙

0

∙

share

This paper proposes integrating semantics-oriented similarity representation into RankingMatch, a recently proposed semi-supervised learning method. Our method, dubbed ReRankMatch, aims to deal with the case in which labeled and unlabeled data share non-overlapping categories. ReRankMatch encourages the model to produce the similar image representations for the samples likely belonging to the same class. We evaluate our method on various datasets such as CIFAR-10, CIFAR-100, SVHN, STL-10, and Tiny ImageNet. We obtain promising results (4.21 CIFAR-100 with 10000 labels, and 2.19 when the amount of labeled data is sufficient to learn semantics-oriented similarity representation.