Semantic Image Segmentation for Efficiently Adding Recognition Objects


Chengnan Lu, Jinho Park, Journal of Information Processing Systems Vol. 18, No. 5, pp. 701-710, Oct. 2022  

10.3745/JIPS.02.0183
Keywords: Image Segmentation, Machine Learning, Object Detection
Fulltext:

Abstract

With the development of artificial intelligence technology, various methods have been developed for recognizing objects in images using machine learning. Image segmentation is the most effective among these methods for recognizing objects within an image. Conventionally, image datasets of various classes are trained simultaneously. In situations where several classes require segmentation, all datasets have to be trained thoroughly. Such repeated training results in low training efficiency because most of the classes have already been trained. In addition, the number of classes that appear in the datasets affects training. Some classes appear in datasets in remarkably smaller numbers than others, and hence, the training errors will not be properly reflected when all the classes are trained simultaneously. Therefore, a new method that separates some classes from the dataset is proposed to improve efficiency during training. In addition, the accuracies of the conventional and proposed methods are compared.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from November 1st, 2017)
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.




Cite this article
[APA Style]
Lu, C. & Park, J. (2022). Semantic Image Segmentation for Efficiently Adding Recognition Objects. Journal of Information Processing Systems, 18(5), 701-710. DOI: 10.3745/JIPS.02.0183.

[IEEE Style]
C. Lu and J. Park, "Semantic Image Segmentation for Efficiently Adding Recognition Objects," Journal of Information Processing Systems, vol. 18, no. 5, pp. 701-710, 2022. DOI: 10.3745/JIPS.02.0183.

[ACM Style]
Chengnan Lu and Jinho Park. 2022. Semantic Image Segmentation for Efficiently Adding Recognition Objects. Journal of Information Processing Systems, 18, 5, (2022), 701-710. DOI: 10.3745/JIPS.02.0183.