RPCANet: Deep Unfolding RPCA Based Infrared Small Target Detection
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
RPCANet : Deep Unfolding RPCA Based Infrared Small Target Detection. / Wu, Fengyi ; Zhang, Tianfang; Li, Lei; Huang, Yian ; Peng, Zhenming.
2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE, 2024. p. 4797-4806.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - RPCANet
T2 - WACV 2024 - IEEE/CVF Winter Conference on Applications of Computer Vision
AU - Wu, Fengyi
AU - Zhang, Tianfang
AU - Li, Lei
AU - Huang, Yian
AU - Peng, Zhenming
PY - 2024
Y1 - 2024
N2 - Deep learning (DL) networks have achieved remarkable performance in infrared small target detection (ISTD). However, these structures exhibit a deficiency in interpretability and are widely regarded as black boxes, as they disregard domain knowledge in ISTD. To alleviate this issue, this work proposes an interpretable deep network for detecting infrared dim targets, dubbed RPCANet. Specifically, our approach formulates the ISTD task as sparse target extraction, low-rank background estimation, and image reconstruction in a relaxed Robust Principle Component Analysis (RPCA) model. By unfolding the iterative optimization updating steps into a deep-learning framework, time-consuming and complex matrix calculations are replaced by theory-guided neural networks. RPCANet detects targets with clear interpretability and preserves the intrinsic image feature, instead of directly transforming the detection task into a matrix decomposition problem. Extensive experiments substantiate the effectiveness of our deep unfolding framework and demonstrate its trustworthy results, surpassing baseline methods in both qualitative and quantitative evaluations. Our source code is available at https://github.com/fengyiwu98/RPCANet.
AB - Deep learning (DL) networks have achieved remarkable performance in infrared small target detection (ISTD). However, these structures exhibit a deficiency in interpretability and are widely regarded as black boxes, as they disregard domain knowledge in ISTD. To alleviate this issue, this work proposes an interpretable deep network for detecting infrared dim targets, dubbed RPCANet. Specifically, our approach formulates the ISTD task as sparse target extraction, low-rank background estimation, and image reconstruction in a relaxed Robust Principle Component Analysis (RPCA) model. By unfolding the iterative optimization updating steps into a deep-learning framework, time-consuming and complex matrix calculations are replaced by theory-guided neural networks. RPCANet detects targets with clear interpretability and preserves the intrinsic image feature, instead of directly transforming the detection task into a matrix decomposition problem. Extensive experiments substantiate the effectiveness of our deep unfolding framework and demonstrate its trustworthy results, surpassing baseline methods in both qualitative and quantitative evaluations. Our source code is available at https://github.com/fengyiwu98/RPCANet.
U2 - 10.1109/WACV57701.2024.00474
DO - 10.1109/WACV57701.2024.00474
M3 - Article in proceedings
SP - 4797
EP - 4806
BT - 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
PB - IEEE
Y2 - 4 January 2024 through 8 January 2024
ER -
ID: 378940371