EAAU-Net: Enhanced Asymmetric Attention U-Net for Infrared Small Target Detection
Detecting infrared small targets lacking texture and shape information in cluttered environments is extremely challenging. With the development of deep learning, convolutional neural network (CNN)-based methods have achieved promising results in generic object detection. However, existing CNN-based...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/16/3200 |
| _version_ | 1797522149637881856 |
|---|---|
| author | Xiaozhong Tong Bei Sun Junyu Wei Zhen Zuo Shaojing Su |
| author_facet | Xiaozhong Tong Bei Sun Junyu Wei Zhen Zuo Shaojing Su |
| author_sort | Xiaozhong Tong |
| collection | DOAJ |
| description | Detecting infrared small targets lacking texture and shape information in cluttered environments is extremely challenging. With the development of deep learning, convolutional neural network (CNN)-based methods have achieved promising results in generic object detection. However, existing CNN-based methods with pooling layers may lose the targets in the deep layers and, thus, cannot be directly applied for infrared small target detection. To overcome this problem, we propose an enhanced asymmetric attention (EAA) U-Net. Specifically, we present an efficient and powerful EAA module that uses both same-layer feature information exchange and cross-layer feature fusion to improve feature representation. In the proposed approach, spatial and channel information exchanges occur between the same layers to reinforce the primitive features of small targets, and a bottom-up global attention module focuses on cross-layer feature fusion to enable the dynamic weighted modulation of high-level features under the guidance of low-level features. The results of detailed ablation studies empirically validate the effectiveness of each component in the network architecture. Compared to state-of-the-art methods, the proposed method achieved superior performance, with an intersection-over-union (IoU) of 0.771, normalised IoU (nIoU) of 0.746, and F-area of 0.681 on the publicly available SIRST dataset. |
| first_indexed | 2024-03-10T08:25:22Z |
| format | Article |
| id | doaj.art-63d1ab5a9fb74d7c90d87e8b82e9304d |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T08:25:22Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-63d1ab5a9fb74d7c90d87e8b82e9304d2023-11-22T09:33:42ZengMDPI AGRemote Sensing2072-42922021-08-011316320010.3390/rs13163200EAAU-Net: Enhanced Asymmetric Attention U-Net for Infrared Small Target DetectionXiaozhong Tong0Bei Sun1Junyu Wei2Zhen Zuo3Shaojing Su4College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaDetecting infrared small targets lacking texture and shape information in cluttered environments is extremely challenging. With the development of deep learning, convolutional neural network (CNN)-based methods have achieved promising results in generic object detection. However, existing CNN-based methods with pooling layers may lose the targets in the deep layers and, thus, cannot be directly applied for infrared small target detection. To overcome this problem, we propose an enhanced asymmetric attention (EAA) U-Net. Specifically, we present an efficient and powerful EAA module that uses both same-layer feature information exchange and cross-layer feature fusion to improve feature representation. In the proposed approach, spatial and channel information exchanges occur between the same layers to reinforce the primitive features of small targets, and a bottom-up global attention module focuses on cross-layer feature fusion to enable the dynamic weighted modulation of high-level features under the guidance of low-level features. The results of detailed ablation studies empirically validate the effectiveness of each component in the network architecture. Compared to state-of-the-art methods, the proposed method achieved superior performance, with an intersection-over-union (IoU) of 0.771, normalised IoU (nIoU) of 0.746, and F-area of 0.681 on the publicly available SIRST dataset.https://www.mdpi.com/2072-4292/13/16/3200infrared small target detectionenhanced asymmetric attention mechanismfeature fusionU-Net |
| spellingShingle | Xiaozhong Tong Bei Sun Junyu Wei Zhen Zuo Shaojing Su EAAU-Net: Enhanced Asymmetric Attention U-Net for Infrared Small Target Detection Remote Sensing infrared small target detection enhanced asymmetric attention mechanism feature fusion U-Net |
| title | EAAU-Net: Enhanced Asymmetric Attention U-Net for Infrared Small Target Detection |
| title_full | EAAU-Net: Enhanced Asymmetric Attention U-Net for Infrared Small Target Detection |
| title_fullStr | EAAU-Net: Enhanced Asymmetric Attention U-Net for Infrared Small Target Detection |
| title_full_unstemmed | EAAU-Net: Enhanced Asymmetric Attention U-Net for Infrared Small Target Detection |
| title_short | EAAU-Net: Enhanced Asymmetric Attention U-Net for Infrared Small Target Detection |
| title_sort | eaau net enhanced asymmetric attention u net for infrared small target detection |
| topic | infrared small target detection enhanced asymmetric attention mechanism feature fusion U-Net |
| url | https://www.mdpi.com/2072-4292/13/16/3200 |
| work_keys_str_mv | AT xiaozhongtong eaaunetenhancedasymmetricattentionunetforinfraredsmalltargetdetection AT beisun eaaunetenhancedasymmetricattentionunetforinfraredsmalltargetdetection AT junyuwei eaaunetenhancedasymmetricattentionunetforinfraredsmalltargetdetection AT zhenzuo eaaunetenhancedasymmetricattentionunetforinfraredsmalltargetdetection AT shaojingsu eaaunetenhancedasymmetricattentionunetforinfraredsmalltargetdetection |