Delving into semi-supervised learning with ranking loss of metric learning메트릭 러닝의 순위 손실을 이용한 준지도 학습의 깊은 탐구

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 102
  • Download : 0
Semi-supervised learning (SSL) is a research field playing a vital role in leveraging unlabeled data. In many applications especially real-world problems, labeled data is often very difficult and costly to obtain, so semi-supervised learning is significantly meaningful in fulfilling the limitation of labeled data. One of the most successful SSL approaches is consistency regularization, encouraging the model to produce unchanged when the input is perturbed. We argue that the inputs from the same class should also have the similar model outputs. Therefore, we unify the idea of consistency regularization SSL approach and metric learning to propose a more powerful SSL method, RankingMatch, for image classification. Our method considers both the perturbed inputs and the similarity among the same-class inputs, encouraging the model to produce the similar outputs for not only the different perturbations of the same input but also the inputs from the same class. Delving into the objective function of metric learning, we introduce a novel objective function, BatchMean Triplet loss, which has the advantage of computational efficiency while taking into account all inputs when computing the loss. Our method achieves state-of-the-art results across many standard SSL benchmarks with various labeled data amounts, including 95.13% accuracy on CIFAR-10 with 250 labels, 77.65% accuracy on CIFAR-100 with 10000 labels, 97.76% accuracy on SVHN with 250 labels, and 97.77% accuracy on SVHN with 1000 labels. We also conduct an ablation study, visualizations, and computational measurements to prove the efficacy of our proposed BatchMean Triplet loss in both terms of classification and computational efficiency.
Kim, Daeyoungresearcher김대영researcher
한국과학기술원 :전산학부,
Issue Date

학위논문(석사) - 한국과학기술원 : 전산학부, 2021.2,[iv, 45 p. :]


Semi-supervised learning▼aMetric learning▼aConsistency regularization▼aBatchMean Triplet loss; 준지도학습▼a메트릭 학습▼a일관성 정규화▼aBatchMean Triplet loss

Appears in Collection
Files in This Item
There are no files associated with this item.


  • mendeley


rss_1.0 rss_2.0 atom_1.0