Saved in:
Bibliographic Details
Main Authors: Bao, Chun, Cao, Jie, Ning, Yaqian, Zhao, Tianhua, Li, Zhijun, Wang, Zechen, Zhang, Li, Hao, Qun
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2311.08747
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917569194098688
author Bao, Chun
Cao, Jie
Ning, Yaqian
Zhao, Tianhua
Li, Zhijun
Wang, Zechen
Zhang, Li
Hao, Qun
author_facet Bao, Chun
Cao, Jie
Ning, Yaqian
Zhao, Tianhua
Li, Zhijun
Wang, Zechen
Zhang, Li
Hao, Qun
contents Infrared small target detection based on deep learning offers unique advantages in separating small targets from complex and dynamic backgrounds. However, the features of infrared small targets gradually weaken as the depth of convolutional neural network (CNN) increases. To address this issue, we propose a novel method for detecting infrared small targets called improved dense nested attention network (IDNANet), which is based on the transformer architecture. We preserve the dense nested structure of dense nested attention network (DNANet) and introduce the Swin-transformer during feature extraction stage to enhance the continuity of features. Furthermore, we integrate the ACmix attention structure into the dense nested structure to enhance the features of intermediate layers. Additionally, we design a weighted dice binary cross-entropy (WD-BCE) loss function to mitigate the negative impact of foreground-background imbalance in the samples. Moreover, we develop a dataset specifically for infrared small targets, called BIT-SIRST. The dataset comprises a significant amount of real-world targets and manually annotated labels, as well as synthetic data and corresponding labels. We have evaluated the effectiveness of our method through experiments conducted on public datasets. In comparison to other state-of-the-art methods, our approach outperforms in terms of probability of detection ($P_d$), false-alarm rate ($F_a$), and mean intersection of union ($mIoU$). The $mIoU$ reaches 90.89\% on the NUDT-SIRST dataset and 79.72\% on the SIRST dataset. The BIT-SIRST dataset and codes are available openly at \href{https://github.com/EdwardBao1006/bit\_sirst}{\color[HTML]{B22222}{https://github.com/EdwardBao1006/bit\_sirst}}.
format Preprint
id arxiv_https___arxiv_org_abs_2311_08747
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Improved Dense Nested Attention Network Based on Transformer for Infrared Small Target Detection
Bao, Chun
Cao, Jie
Ning, Yaqian
Zhao, Tianhua
Li, Zhijun
Wang, Zechen
Zhang, Li
Hao, Qun
Computer Vision and Pattern Recognition
Infrared small target detection based on deep learning offers unique advantages in separating small targets from complex and dynamic backgrounds. However, the features of infrared small targets gradually weaken as the depth of convolutional neural network (CNN) increases. To address this issue, we propose a novel method for detecting infrared small targets called improved dense nested attention network (IDNANet), which is based on the transformer architecture. We preserve the dense nested structure of dense nested attention network (DNANet) and introduce the Swin-transformer during feature extraction stage to enhance the continuity of features. Furthermore, we integrate the ACmix attention structure into the dense nested structure to enhance the features of intermediate layers. Additionally, we design a weighted dice binary cross-entropy (WD-BCE) loss function to mitigate the negative impact of foreground-background imbalance in the samples. Moreover, we develop a dataset specifically for infrared small targets, called BIT-SIRST. The dataset comprises a significant amount of real-world targets and manually annotated labels, as well as synthetic data and corresponding labels. We have evaluated the effectiveness of our method through experiments conducted on public datasets. In comparison to other state-of-the-art methods, our approach outperforms in terms of probability of detection ($P_d$), false-alarm rate ($F_a$), and mean intersection of union ($mIoU$). The $mIoU$ reaches 90.89\% on the NUDT-SIRST dataset and 79.72\% on the SIRST dataset. The BIT-SIRST dataset and codes are available openly at \href{https://github.com/EdwardBao1006/bit\_sirst}{\color[HTML]{B22222}{https://github.com/EdwardBao1006/bit\_sirst}}.
title Improved Dense Nested Attention Network Based on Transformer for Infrared Small Target Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.08747