Balanced active learning method for image classification

Papp Dávid and Szűcs Gábor: Balanced active learning method for image classification. In: Acta cybernetica, (23) 2. pp. 645-658. (2017)

[thumbnail of actacyb_23_2_2017_13.pdf]
Cikk, tanulmány, mű

Download (468kB) | Preview


The manual labeling of natural images is and has always been painstaking and slow process, especially when large data sets are involved. Nowadays, many studies focus on solving this problem, and most of them use active learning, which offers a solution for reducing the number of images that need to be labeled. Active learning procedures usually select a subset of the whole data by iteratively querying the unlabeled instances based on their predicted informativeness. One way of estimating the information content of an image is by using uncertainty sampling as a query strategy. This basic technique can significantly reduce the number of label needed; e.g. to set up a good model for classification. Our goal was to improve this method by balancing the distribution of the already labeled images. This modification is based on a novel metric that we present in this paper. We conducted experiments on two popular data sets to demonstrate the efficiency of our proposed balanced active learning (BAL) approach, and the results showed that it outperforms the basic uncertainty sampling.

Item Type: Article
Journal or Publication Title: Acta cybernetica
Date: 2017
Volume: 23
Number: 2
ISSN: 0324-721X
Page Range: pp. 645-658
Language: English
Place of Publication: Szeged
Related URLs:
DOI: 10.14232/actacyb.23.2.2017.13
Uncontrolled Keywords: Képfeldolgozás - digitális, Képszerkesztés, Képelemzés
Additional Information: Bibliogr.: p. 656-658. ; ill. ; összefoglalás angol nyelven
Subjects: 01. Natural sciences
01. Natural sciences > 01.01. Mathematics
01. Natural sciences > 01.02. Computer and information sciences
Date Deposited: 2018. Feb. 13. 10:28
Last Modified: 2022. Jun. 20. 15:32

Actions (login required)

View Item View Item