AugTarget Data Augmentation for Infrared Small Target Detection
Shengjia Chen, Jiewen Zhu, Luping Ji, Hongjun Pan, Yuhao Xu
Abstract
Sample shortage has always been a frequently-faced problem for the machine-learning models in infrared small target detection. As one of main limitations, it is hampering the further promotion of target detection performance. In this paper, we propose a simple and effective data augmentation scheme, AugTarget, to address this shortage issue of small target samples. Our scheme mainly consists of two crucial algorithms: target augmentation and batch augmentation. The former is designed to generate sufficient targets, by random target representation. The latter is devised to diversify training samples. Moreover, the initially-generated image samples of small targets are further enriched by randomly aggregating the feature representation of different images. The experiments on public datasets demonstrate that our AugTarget could bring an obvious improvement to mean intersection over union (mIoU). Cooperated by the augmentation of our AugTarget, the state-of-the-art (SOTA) method, AGPC could even achieve a distinct performance promotion by 3.03%, 2.17% and 2.63% on MDFA, SIRST-Aug and Merged datasets, respectively. In addition, the experimental results on three baseline models also show the universality & adaptivity of AugTarget to different dataset augmentation. Our source codes are available at https://github.com/UESTC-nnLab/AugTarget.