Base Class Selection for Efficient Target-Guided Few-Shot Classification 


Vol. 47,  No. 10, pp. 1656-1659, Oct.  2022
10.7840/kics.2022.47.10.1656


PDF
  Abstract

Few-shot classification aims to classify unlabeled instances into novel classes given only few-labeled instances. Although various few-shot classification methods have been developed by making use of a large amount of data, called a base set, consisting of instances with base classes, it has been largely underexplored how to select more useful base classes in a given base set for solving a specific few-shot task. In this letter, to solve target-guided few-shot classification, we propose a simple yet efficient base set selection method based on our similarity measure. Through experiments using a real-world dataset, we demonstrate the superiority of our proposed base set selection method.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Related Articles
  Cite this article

[IEEE Style]

K. Jeong and W. Shin, "Base Class Selection for Efficient Target-Guided Few-Shot Classification," The Journal of Korean Institute of Communications and Information Sciences, vol. 47, no. 10, pp. 1656-1659, 2022. DOI: 10.7840/kics.2022.47.10.1656.

[ACM Style]

Kyeong-Joong Jeong and Won-Yong Shin. 2022. Base Class Selection for Efficient Target-Guided Few-Shot Classification. The Journal of Korean Institute of Communications and Information Sciences, 47, 10, (2022), 1656-1659. DOI: 10.7840/kics.2022.47.10.1656.

[KICS Style]

Kyeong-Joong Jeong and Won-Yong Shin, "Base Class Selection for Efficient Target-Guided Few-Shot Classification," The Journal of Korean Institute of Communications and Information Sciences, vol. 47, no. 10, pp. 1656-1659, 10. 2022. (https://doi.org/10.7840/kics.2022.47.10.1656)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880