Title: Prior distributions-based data augmentation for object detection

Authors: Ke Sun; Xiangfeng Luo; Liyan Ma; Shixiong Zhu

Addresses: School of Computer Engineering and Science, Shanghai University, Shanghai, China ' School of Computer Engineering and Science, Shanghai University, Shanghai, China ' School of Computer Engineering and Science, Shanghai University, Shanghai, China ' School of Computer Engineering and Science, Shanghai University, Shanghai, China

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.

Keywords: data augmentation; visual context; prior distributions; object detection.

DOI: 10.1504/IJCSE.2022.120786

International Journal of Computational Science and Engineering, 2022 Vol.25 No.1, pp.34 - 43

Received: 29 Jan 2021
Accepted: 16 Mar 2021
Published online: 08 Feb 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article