Prior distributions-based data augmentation for object detection Online publication date: Tue, 08-Feb-2022
by Ke Sun; Xiangfeng Luo; Liyan Ma; Shixiong Zhu
International Journal of Computational Science and Engineering (IJCSE), Vol. 25, No. 1, 2022
Abstract: To solve the problem of data hungry, data augmentation methods based on cut-and-paste that can explore the visual context are widely used. However, these methods either limit the expansion of the instances diversity of dataset or increase the computational burden. In this paper, we propose a novel data augmentation strategy based on prior distributions, which can be used to guide data augmentation for object detection. On one hand, the method can effectively capture the relationship between the foreground instance and the visual context. On the other hand, it can increase the instances diversity of the original dataset as much as possible. Experimental results show that the performance of the popular object detection model can be effectively improved by expanding the original dataset with our method. Compared with the baseline, our method improves by 0.8 percentage point on PASCAL VOC and 1.1 percentage points higher on cross-data test set.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computational Science and Engineering (IJCSE):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com
Our Blog 
Follow us on Twitter 
Visit us on Facebook