Unsupervised feature learning for self-tuning neural networks

Jongbin Ryu, Ming Hsuan Yang, Jongwoo Lim

Research output: Contribution to journalArticlepeer-review

Abstract

In recent years transfer learning has attracted much attention due to its ability to adapt a well-trained model from one domain to another. Fine-tuning is one of the most widely-used methods which exploit a small set of labeled data in the target domain for adapting the network. Including a few methods using the labeled data in the source domain, most transfer learning methods require labeled datasets, and it restricts the use of transfer learning to new domains. In this paper, we propose a fully unsupervised self-tuning algorithm for learning visual features in different domains. The proposed method updates a pre-trained model by minimizing the triplet loss function using only unlabeled data in the target domain. First, we propose the relevance measure for unlabeled data by the bagged clustering method. Then triplets of the anchor, positive, and negative data points are sampled based on the ranking violations of the relevance scores and the Euclidean distances in the embedded feature space. This fully unsupervised self-tuning algorithm improves the performance of the network significantly. We extensively evaluate the proposed algorithm using various metrics, including classification accuracy, feature analysis, and clustering quality, on five benchmark datasets in different domains. Besides, we demonstrate that applying the self-tuning method on the fine-tuned network help achieve better results.

Original languageEnglish
Pages (from-to)103-111
Number of pages9
JournalNeural Networks
Volume133
DOIs
Publication statusPublished - 2021 Jan

Bibliographical note

Funding Information:
This work was partly supported by Institute of Information & communications Technology Planning & Evaluation (IITP), Korea grant funded by the Korea government(MSIT) (No. 2020-0-01373 , Artificial Intelligence Graduate School Program(Hanyang University)), Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Korea ( NRF-2017R1A6A3A11031193 ), and the NSF CAREER, United States of America Grant #1149783 .

Funding Information:
This work was partly supported by Institute of Information & communications Technology Planning & Evaluation (IITP), Korea grant funded by the Korea government(MSIT) (No. 2020-0-01373, Artificial Intelligence Graduate School Program(Hanyang University)), Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Korea (NRF-2017R1A6A3A11031193), and the NSF CAREER, United States of America Grant #1149783.

Publisher Copyright:
© 2020 Elsevier Ltd

All Science Journal Classification (ASJC) codes

  • Cognitive Neuroscience
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Unsupervised feature learning for self-tuning neural networks'. Together they form a unique fingerprint.

Cite this