Page 103 - 《软件学报》2024年第4期

周植 等: 面向开集识别的稳健测试时适应方法 1681

[37] Shanmugam D, Blalock D, Balakrishnan G, et al. Better aggregation in test-time augmentation. In: Proc. of the 2021 IEEE/CVF
Int’l Conf. on Computer Vision (ICCV). 2021. 1214−1223. [doi: 10.1109/ICCV48922.2021.00125]
[38] Phung VH, Rhee EJ. A high-accuracy model average ensemble of convolutional neural networks for classification of cloud image
patches on small datasets. Applied Sciences, 2019, 9(21): 4500. [doi: 10.3390/app9214500]
[39] Zhou ZH. Ensemble Learning. Springer, 2021.
[40] Saito K, Saenko K. OVANet: One-vs-all network for universal domain adaptation. In: Proc. of the 2021 IEEE/CVF Int’l Conf. on
Computer Vision (ICCV). 2021. 8980−8989. [doi: 10.1109/ICCV48922.2021.00887]
[41] Hendrycks D, Dietterich T. Benchmarking neural network robustness to common corruptions and perturbations. In: Proc. of the 7th
Int’l Conf. on Learning Representations. 2019.
[42] Hendrycks D, Gimpel K. A baseline for detecting misclassified and out-of-distribution examples in neural networks. In: Proc. of the
5th Int’l Conf. on Learning Representations. 2017.
[43] Chen G, Qiao L, Shi Y, et al. Learning open set network with discriminative reciprocal points. In: Proc. of the European Conf. on
Computer Vision (ECCV). 2020. 507−522. [doi: 10.1007/978-3-030-58580-8_30]
[44] He K, Zhang X, Ren S, et al. Identity mappings in deep residual networks. In: Proc. of the European Conf. on Computer Vision
(ECCV). 2016. 630–645. [doi: 10.1007/978-3-319-46493-0_38]
[45] Dhamija AR, Günther M, Boult T. Reducing network agnostophobia. In: Advances in Neural Information Processing Systems. 2018.
9175−9186.

附中文参考文献:
[4] 窦文, 王怀民, 贾焰, 等. 构造基于推荐的 Peer-to-Peer 环境下的 Trust 模型. 软件学报, 2004, 15(4): 571−583. http://www.jos.
org.cn/1000-9825/15/571.htm
[6] 朱鹏飞, 张琬迎, 王煜, 等. 考虑多粒度类相关性的对比式开放集识别方法. 软件学报, 2022, 33(4): 1156−1169. https://www.
jos.org.cn/1000-9825/6468.htm [doi: 10.13328/j.cnki.jos.006468]

周植(1998－), 男, 博士生, CCF 学生会 李宇峰(1983－), 男, 博士, 教授, 博士
员, 主要研究领域为机器学习, 数据挖 生导师, CCF 杰出会员, 主要研究领域为
掘, 分布外泛化, 测试时适应. 机器学习, 数据挖掘, 半监督学习与弱监
督学习, 统计学习与优化及其应用.

张丁楚(2001－), 男, 硕士生, CCF 学生 张敏灵(1979－), 男, 博士, 教授, 博士
会员, 主要研究领域为机器学习, 数据挖 生导师, CCF 杰出会员, 主要研究领域为
掘, 测试时适应. 人工智能, 机器学习, 数据挖掘.