ifUNet++: Iterative Feedback UNet++ for Infrared Small Target Detection
Zhangying Weng, Peng Li, Xin Zhuang, Xuefeng Yan, Lina Gong, Haoran Xie, Mingqiang Wei
Abstract
Small targets are often submerged in the cluttered backgrounds of infrared images. In this paper, we propose an iterative feedback UNet++ for infrared small target detection, dubbed ifUNet++. Unlike most of existing methods, ifU-Net++ enables to concentrate on small targets while weakening the interference of clutter backgrounds. ifUNet++ contains two parts: a simplified UNet++ and an iterative feedback strategy. We reduce the unnecessary nodes of UNet++ and have the simplified UNet++ as our backbone network, avoiding the loss of infrared small targets. Based on the simplified network, we search the infrared small targets in an iterative feedback manner, avoiding the interference of cluttered backgrounds. Besides, to optimize the iterative results, we propose Contextual Multiple Attention (CMA) to enhance the features in each iteration. Experimental results exhibit the clear promotion of ifUNet++ over eight state-of-the-art methods, in terms of noise-robustness and detection accuracy.
BibTeX
@inproceedings{icassp2023_ifunetiterativef,
title = {ifUNet++: Iterative Feedback UNet++ for Infrared Small Target Detection},
author = {Zhangying Weng and Peng Li and Xin Zhuang and Xuefeng Yan and Lina Gong and Haoran Xie and Mingqiang Wei},
booktitle = {ICASSP 2023},
year = {2023}
}