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% error rate on CIFAR-10 with 4000 labels, 22.32% error rate on CIFAR-100 with 10000 labels, and 2.19% error rate on SVHN with 1000 labels) when the amount of labeled data is sufficient to learn semantics-oriented similarity representation. The code is made publicly available at https://github.com/tqtrunghnvn/ReRankMatch.
翻译:本文建议将语义导向的相似性表述纳入排名Match, 这是最近提出的一种半监督的学习方法。 我们的方法称为 ReRankMatch, 旨在处理标签和无标签数据共享非重叠类别的案例。 ReRankMatch 鼓励模型为可能属于同一类的样本制作类似的图像表达方式。 我们评估了我们在各种数据集上的方法,如CIFAR-10、CIFAR-100、SVHN、STL-10和Tiny图像Net。 当标签数量足以学习以语义为导向的类似表达方式时, 我们获得了有希望的结果( CIFAR- 10和4000个标签的误差率为4.21%,CIFAR- 100和1 000个标签的误差率为22.32%, SVHN和1 000个标签的误差率为2.19% 。 当标签数据的数量足以学习以语义为导向的类似表达方式时, 我们的代码公布在 https://github.com/tqrunghn/ReankMatch/ReankMatch上。