The search functionality is under construction.
The search functionality is under construction.

Semi-Supervised Representation Learning via Triplet Loss Based on Explicit Class Ratio of Unlabeled Data

Kazuhiko MURASAKI, Shingo ANDO, Jun SHIMAMURA

  • Full Text Views

    0

  • Cite this

Summary :

In this paper, we propose a semi-supervised triplet loss function that realizes semi-supervised representation learning in a novel manner. We extend conventional triplet loss, which uses labeled data to achieve representation learning, so that it can deal with unlabeled data. We estimate, in advance, the degree to which each label applies to each unlabeled data point, and optimize the loss function with unlabeled features according to the resulting ratios. Since the proposed loss function has the effect of adjusting the distribution of all unlabeled data, it complements methods based on consistency regularization, which has been extensively studied in recent years. Combined with a consistency regularization-based method, our method achieves more accurate semi-supervised learning. Experiments show that the proposed loss function achieves a higher accuracy than the conventional fine-tuning method.

Publication
IEICE TRANSACTIONS on Information Vol.E105-D No.4 pp.778-784
Publication Date
2022/04/01
Publicized
2022/01/17
Online ISSN
1745-1361
DOI
10.1587/transinf.2021EDP7073
Type of Manuscript
PAPER
Category
Image Recognition, Computer Vision

Authors

Keyword