Page 458 - 《软件学报》2024年第6期

3034 软件学报 2024 年第 35 卷第 6 期

[19] Inoue H. Data augmentation by pairing samples for images classification. arXiv:1801.02929, 2018.
[20] Netzer Y, Wang T, Coates A, Bissacco A, Wu B, Ng AY. Reading digits in natural images with unsupervised feature learning. In: Proc.
of the 2011 NIPS Workshop on Deep Learning and Unsupervised Feature Learning. Granada: NIPS, 2011. 1–9.
[21] Piczak KJ. ESC: Dataset for environmental sound classification. In: Proc. of the 23rd ACM Int’l Conf. on Multimedia. Brisbane: ACM,
2015. 1015–1018. [doi: 10.1145/2733373.2806390]
[22] Tzanetakis G, Cook P. Musical genre classification of audio signals. IEEE Trans. on Speech and Audio Processing, 2002, 10(5): 293–302.
[doi: 10.1109/tsa.2002.800560]
[23] Zhang X, Zhao JB, LeCun Y. Character-level convolutional networks for text classification. In: Proc. of the 28th Int’l Conf. on Neural
Information Processing Systems. Montréal: MIT Press, 2015. 649–657.
[24] Auer S, Bizer C, Kobilarov G, Lehmann J, Cyganiak R, Ives Z. DBpedia: A nucleus for a web of open data. In: Proc. of the 6th Int’l
Semantic Web Conf. and the 2nd Asian Semantic Web Conf. Busan: Springer, 2007. 722–735. [doi: 10.1007/978-3-540-76298-0_52]
[25] He KM, Zhang XY, Ren SQ, Sun J. Deep residual learning for image recognition. In: Proc. of the 2016 IEEE/CVF Conf. on Computer
Vision and Pattern Recognition (CVPR). Las Vegas: IEEE, 2016. 770–778. [doi: 10.1109/cvpr.2016.90]
[26] Zagoruyko S, Komodakis N. Wide residual networks. In: Proc. of the 2016 British Machine Vision Conf. (BMVC). York: BMVA Press,
2016. 87.1–87.12. [doi: 10.5244/c.30.87]

[27] Gastaldi X. Shake-shake regularization. arXiv:1705.07485, 2017.
[28] Szegedy C, Liu W, Jia YQ, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions.
In: Proc. of the 2015 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). Boston: IEEE, 2015. 1–9. [doi: 10.1109/cvpr.
2015.7298594]
[29] Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv:1412.6980, 2014.
[30] Huang G, Liu Z, van der Maaten L, Weinberger KQ. Densely connected convolutional networks. In: Proc. of the 2017 IEEE Conf. on
Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE, 2017. 2261–2269. [doi: 10.1109/cvpr.2017.243]
[31] Joulin A, Grave É, Bojanowski P, Mikolov T. Bag of tricks for efficient text classification. In: Proc. of the 15th Conf. of the European
Chapter of the Association for Computational Linguistics, Vol. 2 (Short Papers). Valencia: Association for Computational Linguistics,
2017. 427–431. [doi: 10.18653/v1/e17-2068]
[32] Chen YH. Convolutional neural network for sentence classification [MS. Thesis]. Waterloo: University of Waterloo, 2015.
[33] Zhou P, Shi W, Tian J, Qi ZY, Li BC, Hao HW, Xu B. Attention-based bidirectional long short-term memory networks for relation
classification. In: Proc. of the 54th Annual Meeting of the Association for Computational Linguistics, Vol. 2 (Short Papers). Berlin:
Association for Computational Linguistics, 2016. 207–212. [doi: 10.18653/v1/p16-2034]
[34] Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I. Attention is all you need. In: Proc. of the
31th Int’l Conf. on Neural Information Processing Systems. Long Beach: Curran Associates Inc., 2017. 6000–6010.
[35] Mania H, Guy A, Recht B. Simple random search provides a competitive approach to reinforcement learning. arXiv:1803.07055, 2018.
[36] Feurer M, Klein A, Eggensperger K, Springenberg JT, Blum M, Hutter F. Efficient and robust automated machine learning. In: Proc. of
the 28th Int’l Conf. on Neural Information Processing Systems. Montréal: MIT Press, 2015. 2755–2763.
[37] Thornton C, Hutter F, Hoos HH, Leyton-Brown K. Auto-WEKA: Combined selection and hyperparameter optimization of classification
algorithms. In: Proc. of the 19th ACM SIGKDD Int’l Conf. on Knowledge Discovery and Data Mining (KDD). Chicago: Association for
Computing Machinery, 2013. 847–855. [doi: 10.1145/2487575.2487629]
[38] Qian C. Multiobjective evolutionary algorithms are still good: Maximizing monotone approximately submodular minus modular
functions. Evolutionary Computation, 2021, 29(4): 463–490. [doi: 10.1162/evco_a_00288]

附录 A

表 A1–表 A3 分别为本文采用的图像、语音、文本数据增强策略.
表 A1 13 种图像数据增强函数以及增强幅度取值范围

增强函数 描述 增强幅度取值范围
ShearX (Y) 以某个幅度沿X (Y)轴剪切图像(0.5的概率取反) [–0.3, 0.3]
TranslateX (Y) 以某个幅度在X (Y)轴方向上平移图像(0.5的概率取反) [–150, 150]
Rotate 以某个幅度旋转图像(0.5的概率取反) [–30, 30]