IRFR-Net: Interactive Recursive Feature-Reshaping Network for Detecting Salient Objects in RGB-D Images
IEEE Transactions on Neural Networks and Learning Systems · 2025-03 · 36 (3) · 4132-4144
DOI: 10.1109/tnnls.2021.3105484 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Neural Networks and Learning Systems, 2025-03. Verfasst von Wujie Zhou und 4 weiteren Autor:innen. Die Arbeit wurde bisher 110-mal zitiert (Crossref) und nennt 69 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Zhejiang Provincial Natural Science Foundation of China.
Abstract (Originalsprache)
Using attention mechanisms in saliency detection networks enables effective feature extraction, and using linear methods can promote proper feature fusion, as verified in numerous existing models. Current networks usually combine depth maps with red-green-blue (RGB) images for salient object detection (SOD). However, fully leveraging depth information complementary to RGB information by accurately highlighting salient objects deserves further study. We combine a gated attention mechanism and a linear fusion method to construct a dual-stream interactive recursive feature-reshaping network (IRFR-Net). The streams for RGB and depth data communicate through a backbone encoder to thoroughly extract complementary information. First, we design a context extraction module (CEM) to obtain low-level depth foreground information. Subsequently, the gated attention fusion module (GAFM) is applied to the RGB depth (RGB-D) information to obtain advantageous structural and spatial fusion features. Then, adjacent depth information is globally integrated to obtain complementary context features. We also introduce a weighted atrous spatial pyramid pooling (WASPP) module to extract the multiscale local information of depth features. Finally, global and local features are fused in a bottom-up scheme to effectively highlight salient objects. Comprehensive experiments on eight representative datasets demonstrate that the proposed IRFR-Net outperforms 11 state-of-the-art (SOTA) RGB-D approaches in various evaluation indicators.
Förderung
- National Natural Science Foundation of China
- Zhejiang Provincial Natural Science Foundation of China
Zitieren
APA
Zhou, W., Guo, Q., Lei, J., Yu, L., & Hwang, J. N. (2025). IRFR-Net: Interactive Recursive Feature-Reshaping Network for Detecting Salient Objects in RGB-D Images. IEEE Transactions on Neural Networks and Learning Systems, 36(3), 4132-4144. https://doi.org/10.1109/tnnls.2021.3105484
Vancouver
Zhou W, Guo Q, Lei J, Yu L, Hwang JN. IRFR-Net: Interactive Recursive Feature-Reshaping Network for Detecting Salient Objects in RGB-D Images. IEEE Transactions on Neural Networks and Learning Systems. 2025;36(3):4132-4144. doi:10.1109/tnnls.2021.3105484
BibTeX
@article{Zhou2025,
author = {Zhou, Wujie and Guo, Qinling and Lei, Jingsheng and Yu, Lu and Hwang, Jenq-Neng},
title = {IRFR-Net: Interactive Recursive Feature-Reshaping Network for Detecting Salient Objects in RGB-D Images},
journal = {IEEE Transactions on Neural Networks and Learning Systems},
year = {2025},
volume = {36},
number = {3},
pages = {4132--4144},
doi = {10.1109/tnnls.2021.3105484}
}
EUVIMED