Page 489 - 《软件学报》2026年第2期

968 软件学报 2026 年第 37 卷第 2 期

the 27th Int’l Joint Conf. on Artificial Intelligence. Stockholm: AAAI Press, 2018. 698–704. [doi: 10.5555/3304415.3304515]
[27] Hodson TO. Root-mean-square error (RMSE) or mean absolute error (MAE): When to use them or not. Geoscientific Model
Development, 2022, 15(14): 5481–5487. [doi: 10.5194/gmd-15-5481-2022]
[28] Ruder S. An overview of gradient descent optimization algorithms. arXiv:1609.04747, 2016.
[29] Loshchilov I, Hutter F. SGDR: Stochastic gradient descent with warm restarts. In: Proc. of the 5th Int’l Conf. on Learning
Representations. 2017.
[30] Wu Z, Su L, Huang QM. Cascaded partial decoder for fast and accurate salient object detection. In: Proc. of the 2019 IEEE/CVF Conf. on
Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019. 3902–3911. [doi: 10.1109/CVPR.2019.00403]
[31] Wu Z, Su L, Huang QM. Stacked cross refinement network for edge-aware salient object detection. In: Proc. of the 2019 IEEE/CVF Int’l
Conf. on Computer Vision. Seoul: IEEE, 2019. 7263–7272. [doi: 10.1109/ICCV.2019.00736]
[32] Zhao JW, Zhao YF, Li J, Chen XW. Is depth really necessary for salient object detection? In: Proc. of the 28th ACM Int’l Conf. on
Multimedia. Seattle: ACM, 2020. 1745–1754. [doi: 10.1145/3394171.3413855]
[33] Wei J, Wang SH, Huang QM. F³Net: Fusion, feedback and focus for salient object detection. In: Proc. of the 34th AAAI Conf. on
Artificial Intelligence. New York: AAAI Press, 2020. 12321–12328. [doi: 10.1609/aaai.v34i07.6916]
[34] Chen ZY, Xu QQ, Cong RM, Huang QM. Global context-aware progressive aggregation network for salient object detection. In: Proc. of
the 34th AAAI Conf. on Artificial Intelligence. New York: AAAI Press, 2020. 10599–10606. [doi: 10.1609/aaai.v34i07.6633]
[35] Zhou HJ, Xie XH, Lai JH, Chen ZX, Yang LX. Interactive two-stream decoder for accurate and fast saliency detection. In: Proc. of the
2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020. 9138–9147. [doi: 10.1109/CVPR42600.2020.
00916]
[36] Wei J, Wang SH, Wu Z, Su C, Huang QM, Tian Q. Label decoupling framework for salient object detection. In: Proc. of the 2020
IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020. 13022–13031. [doi: 10.1109/CVPR42600.2020.
01304]
[37] Zhao ZR, Xia CQ, Xie CX, Li J. Complementary trilateral decoder for fast and accurate salient object detection. In: Proc. of the 29th
ACM Int’l Conf. on Multimedia. ACM, 2021. 4967–4975. [doi: 10.1145/3474085.3475494]
[38] Ma MC, Xia CQ, Li J. Pyramidal feature shrinking for salient object detection. In: Proc. of the 35th AAAI Conf. on Artificial
Intelligence. AAAI Press, 2021. 2311–2318. [doi: 10.1609/aaai.v35i3.16331]
[39] Yun YK, Lin WS. Towards a complete and detail-preserved salient object detection. IEEE Trans. on Multimedia, 2024, 26: 4667–4680.
[doi: 10.1109/TMM.2023.3325731]

附中文参考文献
[1] 丛润民, 张晨, 徐迈, 刘鸿羽, 赵耀. 深度学习时代下的 RGB-D 显著性目标检测研究进展. 软件学报, 2023, 34(4): 1711–1731. http://
www.jos.org.cn/1000-9825/6700.htm [doi: 10.13328/j.cnki.jos.006700]

作者简介
童彪, 硕士生, 主要研究领域为人工智能, 显著性目标检测.
宋晓宁, 博士, 教授, 博士生导师, CCF 专业会员, 主要研究领域为模式识别, 计算机视觉, 生物信息学, 机器学习.
华阳, 博士生, 主要研究领域为生物信息学, 计算机视觉, 深度学习.
张文杰, 博士生, 主要研究领域为自然语言处理, 信息抽取.
吴小俊, 博士, 教授, 博士生导师, 主要研究领域为模式识别, 计算机视觉, 生物信息学, 机器学习.