Boosting Salient Object Detection With Transformer-Based Asymmetric Bilateral U-Net
IEEE Transactions on Circuits and Systems for Video Technology · 2024-04 · 34 (4) · 2332-2345
DOI: 10.1109/tcsvt.2023.3307693 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2024-04. Verfasst von Yu Qiu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 47-mal zitiert (Crossref) und nennt 97 Literaturangaben. Gefördert von: China Postdoctoral Science Foundation, Tianjin Research Innovation Project for Postgraduate Students.
Abstract (Originalsprache)
Existing salient object detection (SOD) methods mainly rely on U-shaped convolution neural networks (CNNs) with skip connections to combine the global contexts and local spatial details that are crucial for locating salient objects and refining object details, respectively. Despite great successes, the ability of CNNs in learning global contexts is limited. Recently, the vision transformer has achieved revolutionary progress in computer vision owing to its powerful modeling of global dependencies. However, directly applying the transformer to SOD is suboptimal because the transformer lacks the ability to learn local spatial representations. To this end, this paper explores the combination of transformers and CNNs to learn both global and local representations for SOD. We propose a transformer-based Asymmetric Bilateral U-Net (ABiU-Net). The asymmetric bilateral encoder has a transformer path and a lightweight CNN path, where the two paths communicate at each encoder stage to learn complementary global contexts and local spatial details, respectively. The asymmetric bilateral decoder also consists of two paths to process features from the transformer and CNN encoder paths, with communication at each decoder stage for decoding coarse salient object locations and fine-grained object details, respectively. Such communication between the two encoder/decoder paths enables AbiU-Net to learn complementary global and local representations, taking advantage of the natural merits of transformers and CNNs, respectively. Hence, ABiU-Net provides a new perspective for transformer-based SOD. Extensive experiments demonstrate that ABiU-Net performs favorably against previous state-of-the-art SOD methods. The code is available at https://github.com/yuqiuyuqiu/ABiU-Net.
Förderung
- China Postdoctoral Science Foundation
- Tianjin Research Innovation Project for Postgraduate Students
Zitieren
APA
Qiu, Y., Liu, Y., Zhang, L., Lu, H., & Xu, J. (2024). Boosting Salient Object Detection With Transformer-Based Asymmetric Bilateral U-Net. IEEE Transactions on Circuits and Systems for Video Technology, 34(4), 2332-2345. https://doi.org/10.1109/tcsvt.2023.3307693
Vancouver
Qiu Y, Liu Y, Zhang L, Lu H, Xu J. Boosting Salient Object Detection With Transformer-Based Asymmetric Bilateral U-Net. IEEE Transactions on Circuits and Systems for Video Technology. 2024;34(4):2332-2345. doi:10.1109/tcsvt.2023.3307693
BibTeX
@article{Qiu2024,
author = {Qiu, Yu and Liu, Yun and Zhang, Le and Lu, Haotian and Xu, Jing},
title = {Boosting Salient Object Detection With Transformer-Based Asymmetric Bilateral U-Net},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2024},
volume = {34},
number = {4},
pages = {2332--2345},
doi = {10.1109/tcsvt.2023.3307693}
}
EUVIMED