A study on fire data augmentation from video/image using the Similar-label and F-guessed method

Jong-Sik Kim1 and Dae-Seong Kang1

  1. Dept. of Electronics Engineering, Dong-A University,37 Nakdong-daero 550 beon-gil
    Saha-gu, Busan, Korea
    kjsluke, dskang@dau.ac.kr

Abstract

When data collection is limited, such as in the case of fire detection, improving the detection rate with only number of small labeled data is difficult. Therefore, researchers have conducted many related studies, among which semisupervised learning methods have achieved good results in improving detection rates. Most recent semi-supervised learning models use the pseudo-label method. But there is a problem, which is that it is difficult to label accurately in samples that deviate from the true label distribution due to false labels. In other words, due to the pseudo-label used for data augmentation, erroneous biases can be accumulated and adversely affect the final weights. To improve this, we proposed a method of generating Similar-labeled data (prediction result labeling value and correct answer value are similar), which was used through the F-guessed method and the Region of Interest (ROI) expression method in the video during initial learning. This has the effect of preventing the bias from being distorted in the initial stages. As a result, data generation increased by about 6.5 times, from 5,565 to 41,712, mAP@0.5 increased by about 26.1%, from 65.9% to 92.0%, and loss improved from 3.347 to 1.69, compared to the initial labeled data.

Key words

semi-supervised learning, deep learning, pseudo-labeling, fine-tuning, Similar-label, F-guessed

Digital Object Identifier (DOI)

https://doi.org/10.2298/CSIS230820011K

Publication information

Volume 21, Issue 2 (April 2024)
Special Issue on Deep Learning Techniques in Intelligent Internet of Things and 5G Communication Networks
Year of Publication: 2024
ISSN: 2406-1018 (Online)
Publisher: ComSIS Consortium

Full text

DownloadAvailable in PDF
Portable Document Format

How to cite

Kim, J., Kang, D.: A study on fire data augmentation from video/image using the Similar-label and F-guessed method. Computer Science and Information Systems, Vol. 21, No. 2, 645–661. (2024), https://doi.org/10.2298/CSIS230820011K