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

TL;DR

ReRankMatch enhances semi-supervised learning by integrating semantics-oriented similarity representations, improving classification accuracy especially when labeled and unlabeled data have non-overlapping categories.

Contribution

It introduces ReRankMatch, a novel method that incorporates semantics-oriented similarity into RankingMatch to better handle non-overlapping categories in semi-supervised learning.

Findings

Achieves 4.21% error on CIFAR-10 with 4000 labels

Achieves 22.32% error on CIFAR-100 with 10000 labels

Achieves 2.19% error on SVHN with 1000 labels

Abstract

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.