本論文針對資料稀缺環境下的感應電動機故障診斷問題，提出一套結合生成對抗網路（Wasserstein GAN with Gradient Penalty, WGAN-GP）資料增強與 ResNet50 深度卷積神經網路的分類方法。研究流程包括：首先，利用連續小波轉換（Continuous Wavelet Transform, CWT）將一維振動SS訊號轉換為二維時頻圖，以提升特徵可分性；其次，採用 WGAN-GP 生成合成樣本，緩解原始資料量不足的問題；最後，以 ResNet50 進行分類訓練與效能評估。本論文設計系統性實驗，分析三種不同資料增強比例對分類效能的影響，包含：B20（合成資料佔20%、真實資料佔80%）、B50（各佔50%）、B80（合成資料佔80%、真實資料佔20%）。實驗除了分析分類準確度，亦以FID、IS指標及t-SNE視覺化評估生成樣本品質與多樣性。結果顯示，適度資料增強（如B50）可有效提升分類效能，並經Wilcoxon Signed-Rank Test統計檢定證實其提升具顯著性。此外，本研究亦探討資料增強對少數類別辨識能力的提升，並於不同高斯雜訊強度下測試分類模型之穩健性。綜合而言，本方法能顯著提升感應電動機故障診斷之準確性，並具備實務應用潛力，可作為後續工業感應電動機診斷系統開發的重要參考依據。

This thesis addresses the challenge of induction motor fault diagnosis under data-scarce conditions by proposing an integrated method that combines data augmentation using the Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) and classification via a deep convolutional neural network (ResNet50). One-dimensional vibration signals are first converted into two-dimensional time-frequency representations using the Continuous Wavelet Transform (CWT), which enhances feature separability for nonstationary signals. WGAN-GP is then employed to generate high-quality synthetic samples, thereby enriching the training set and mitigating the limitations posed by insufficient real data. Systematic experiments were conducted to evaluate various augmentation ratios (20%, 50%, 80%) in terms of classification accuracy, weighted F1-score, AUC, and sample quality metrics, including Fréchet Inception Distance (FID), Inception Score (IS), and t-SNE visualizations. Statistical significance was assessed via the Wilcoxon Signed-Rank Test. The results indicate that a moderate augmentation ratio (50%) yields optimal performance, nearly matching the accuracy of the full-data baseline and significantly surpassing the low-resource model, especially in minority-class recognition. Additionally, the proposed method demonstrates strong robustness under simulated noise conditions, maintaining high classification accuracy. Overall, this approach substantially improves diagnostic performance in limited data scenarios and provides practical value for real-world industrial applications.

[1]P. J. Zhang, Y. Du, T. G. Habetler, and B. Lu, "A Survey of Condition Monitoring and Protection Methods for Medium-Voltage Induction Motors," Ieee Transactions on Industry Applications, vol. 47, no. 1, pp. 34-46, Jan-Feb 2011, doi: 10.1109/tia.2010.2090839.
[2]F. Filippetti, A. Bellini, and G.-A. Capolino, "Condition monitoring and diagnosis of rotor faults in induction machines: State of art and future perspectives," in 2013 IEEE Workshop on Electrical Machines Design, Control and Diagnosis (WEMDCD), 2013: IEEE, pp. 196-209.
[3]M. E. Benbouzid, "A review of induction motors signature analysis as a medium for faults detection," Ieee Transactions on Industrial Electronics, vol. 47, no. 5, pp. 984-993, Oct 2000. [Online]. Available: <Go to ISI>://WOS:000089765100002.
[4]A. Widodo and B.-S. Yang, "Support vector machine in machine condition monitoring and fault diagnosis," Mechanical systems and signal processing, vol. 21, no. 6, pp. 2560-2574, 2007.
[5]Y. Lei, B. Yang, X. Jiang, F. Jia, N. Li, and A. K. Nandi, "Applications of machine learning to machine fault diagnosis: A review and roadmap," Mechanical systems and signal processing, vol. 138, p. 106587, 2020.
[6]W. Zhang, C. Li, G. Peng, Y. Chen, and Z. Zhang, "A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load," Mechanical systems and signal processing, vol. 100, pp. 439-453, 2018.
[7]R. Zhao, R. Yan, Z. Chen, K. Mao, P. Wang, and R. X. Gao, "Deep learning and its applications to machine health monitoring," Mechanical Systems and Signal Processing, vol. 115, pp. 213-237, 2019.
[8]R. Liu, B. Yang, E. Zio, and X. Chen, "Artificial intelligence for fault diagnosis of rotating machinery: A review," Mechanical Systems and Signal Processing, vol. 108, pp. 33-47, 2018.
[9]M. Frid-Adar, E. Klang, M. Amitai, J. Goldberger, and H. Greenspan, "Synthetic data augmentation using GAN for improved liver lesion classification," in 2018 IEEE 15th international symposium on biomedical imaging (ISBI 2018), 2018: IEEE, pp. 289-293.
[10]X. Yi, E. Walia, and P. Babyn, "Generative adversarial network in medical imaging: A review," Medical image analysis, vol. 58, p. 101552, 2019.
[11]T. Y. Pan, J. L. Chen, T. C. Zhang, S. Liu, S. L. He, and H. X. Lv, "Generative adversarial network in mechanical fault diagnosis under small sample: A systematic review on applications and future perspectives," Isa Transactions, vol. 128, pp. 1-10, Sep 2022, doi: 10.1016/j.isatra.2021.11.040.
[12]S. Durgam, L. N. Bawankule, and P. S. Khindkar, "Prediction of fault detection based on vibration analysis for motor applications," in 2021 4th Biennial International Conference on Nascent Technologies in Engineering (ICNTE), 2021: IEEE, pp. 1-5.
[13]M. K. Babouri, N. Ouelaa, T. Kebabsa, and A. Djebala, "Application of the cyclostationarity analysis in the detection of mechanical defects: comparative study," The International Journal of Advanced Manufacturing Technology, vol. 103, pp. 1681-1699, 2019.
[14]A. Lay-Ekuakille, G. Griffo, P. Visconti, P. Primiceri, and R. Velazquez, "Leak detection in waterworks: comparison between STFT and FFT with an overcoming of limitations," Metrology and Measurement Systems, vol. 24, no. 4, pp. 631-644, 2017.
[15]J. Du, X. Li, Y. Gao, and L. Gao, "Integrated gradient-based continuous wavelet transform for bearing fault diagnosis," Sensors, vol. 22, no. 22, p. 8760, 2022.
[16]X. F. Zhao, L. B. Wang, M. S. Yang, Y. Chen, and J. W. Xiang, "A Novel Small-Sample Fault Diagnosis Method for Rolling Bearings via Continuous Wavelet Transform and Siamese Neural Network," Ieee Sensors Journal, vol. 24, no. 15, pp. 24988-24996, Aug 2024, doi: 10.1109/jsen.2024.3409768.
[17]K. A. Loparo, M. L. Adams, W. Lin, M. F. Abdel-Magied, and N. Afshari, "Fault detection and diagnosis of rotating machinery," Ieee Transactions on Industrial Electronics, vol. 47, no. 5, pp. 1005-1014, Oct 2000. [Online]. Available: <Go to ISI>://WOS:000089765100004.
[18]V. K. Rai and A. R. Mohanty, "Bearing fault diagnosis using FFT of intrinsic mode functions in Hilbert-Huang transform," Mechanical Systems and Signal Processing, vol. 21, no. 6, pp. 2607-2615, Aug 2007, doi: 10.1016/j.ymssp.2006.12.004.
[19]N. H. Chandra and A. S. Sekhar, "Fault detection in rotor bearing systems using time frequency techniques," Mechanical Systems and Signal Processing, vol. 72-73, pp. 105-133, May 2016, doi: 10.1016/j.ymssp.2015.11.013.
[20]M. J. Hasan, A. Rai, Z. Ahmad, and J. M. Kim, "A Fault Diagnosis Framework for Centrifugal Pumps by Scalogram-Based Imaging and Deep Learning," Ieee Access, vol. 9, pp. 58052-58066, 2021, doi: 10.1109/access.2021.3072854.
[21]X. Z. Xu, X. Q. Chen, and Y. J. Zhao, "Data imbalance bearing fault diagnosis based on fusion attention mechanism and global feature cross GAN network," Measurement Science and Technology, vol. 35, no. 10, Oct 2024, Art no. 106136, doi: 10.1088/1361-6501/ad64f5.
[22]R. Wang, S. Zhang, Z. Chen, and W. Li, "Enhanced generative adversarial network for extremely imbalanced fault diagnosis of rotating machine," Measurement, vol. 180, p. 109467, 2021.
[23]J. Liu, C. Zhang, and X. Jiang, "Imbalanced fault diagnosis of rolling bearing using improved MsR-GAN and feature enhancement-driven CapsNet," Mechanical Systems and Signal Processing, vol. 168, p. 108664, 2022.
[24]J. Li, Y. Liu, and Q. Li, "Generative adversarial network and transfer-learning-based fault detection for rotating machinery with imbalanced data condition," Measurement Science and Technology, vol. 33, no. 4, p. 045103, 2022.
[25]S. Chatterjee and Y.-C. Byun, "Leveraging Generative Adversarial Networks for Data Augmentation to Improve Fault Detection in Wind Turbines with Imbalanced Data," Results in Engineering, p. 103991, 2025.
[26]I. J. Goodfellow et al., "Generative adversarial nets," Advances in neural information processing systems, vol. 27, 2014.
[27]A. Radford, L. Metz, and S. Chintala, "Unsupervised representation learning with deep convolutional generative adversarial networks," arXiv preprint arXiv:1511.06434, 2015.
[28]Y. He, H. Tang, Y. Ren, and A. Kumar, "A semi-supervised fault diagnosis method for axial piston pump bearings based on DCGAN," Measurement science and technology, vol. 32, no. 12, p. 125104, 2021.
[29]H. Zhu and T. Fang, "Compound fault diagnosis of rolling bearings with few-shot based on DCGAN-RepLKNet," Measurement Science and Technology, vol. 35, no. 6, p. 066105, 2024.
[30]F. Sheng-Wei and L. Ying-Zhe, "Unbalanced Data-Based Fault Diagnosis Method of Bearing Utilizing Time-Frequency DCGAN Processing," Mechanika, vol. 30, no. 4, 2024.
[31]H. Jeon and D. Lee, "A New Data augmentation method for time series wearable sensor data using a learning mode switching-based DCGAN," IEEE Robotics and Automation Letters, vol. 6, no. 4, pp. 8671-8677, 2021.
[32]M. Arjovsky, S. Chintala, and L. Bottou, "Wasserstein generative adversarial networks," in International conference on machine learning, 2017: PMLR, pp. 214-223.
[33]I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A. C. Courville, "Improved training of wasserstein gans," Advances in neural information processing systems, vol. 30, 2017.
[34]J. Li, T. Liu, and X. Wu, "Research on bearing vibration signal generation method based on filtering WGAN_GP with small samples," Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, vol. 237, no. 20, pp. 4911-4929, 2023.
[35]H. Wang et al., "Data-Augmentation Based CBAM-ResNet-GCN Method for Unbalance Fault Diagnosis of Rotating Machinery," IEEE Access, 2024.
[36]Y. Wang, J. Yan, Z. Yang, Q. Jing, J. Wang, and Y. Geng, "GAN and CNN for imbalanced partial discharge pattern recognition in GIS," High Voltage, vol. 7, no. 3, pp. 452-460, 2022.
[37]X. Zhou, Y. Hu, J. Wu, W. Liang, J. Ma, and Q. Jin, "Distribution bias aware collaborative generative adversarial network for imbalanced deep learning in industrial IoT," IEEE Transactions on Industrial Informatics, vol. 19, no. 1, pp. 570-580, 2022.
[38]M. Heusel, H. Ramsauer, T. Unterthiner, B. Nessler, and S. Hochreiter, "Gans trained by a two time-scale update rule converge to a local nash equilibrium," Advances in neural information processing systems, vol. 30, 2017.
[39]C.-Y. Sue, C.-L. Hsiao, and C.-K. Yeh, "Micromachined capacitive vibration sensor with high passband flatness for condition based monitoring," in 2020 IEEE Eurasia Conference on IOT, Communication and Engineering (ECICE), 2020: IEEE, pp. 144-148.
[40]E. Ben Seddik El Yahyaoui, "Estudi sobre la placa de desenvolupament STM32F4 Discovery," Universitat Politècnica de Catalunya, 2023.
[41]S. Nandi, H. A. Toliyat, and X. Li, "Condition monitoring and fault diagnosis of electrical motors—A review," IEEE transactions on energy conversion, vol. 20, no. 4, pp. 719-729, 2005.
[42]S. A. McInerny and Y. Dai, "Basic vibration signal processing for bearing fault detection," IEEE Transactions on education, vol. 46, no. 1, pp. 149-156, 2003.
[43]G. Stone and J. Kapler, "Stator winding monitoring," IEEE Industry Applications Magazine, vol. 4, no. 5, pp. 15-20, 1998.
[44]G. Kliman, R. Koegl, J. Stein, R. Endicott, and M. Madden, "Noninvasive detection of broken rotor bars in operating induction motors," IEEE Transactions on Energy Conversion, vol. 3, no. 4, pp. 873-879, 1988.
[45]M. H. Lim and M. Leong, "Detection of early faults in rotating machinery based on wavelet analysis," Advances in Mechanical Engineering, vol. 5, p. 625863, 2013.
[46]H. Shao, M. Xia, J. Wan, and C. W. de Silva, "Modified stacked autoencoder using adaptive Morlet wavelet for intelligent fault diagnosis of rotating machinery," IEEE/ASME Transactions on Mechatronics, vol. 27, no. 1, pp. 24-33, 2021.
[47]S. Mallat, A wavelet tour of signal processing. Elsevier, 1999.
[48]Z. K. Peng and F. Chu, "Application of the wavelet transform in machine condition monitoring and fault diagnostics: a review with bibliography," Mechanical systems and signal processing, vol. 18, no. 2, pp. 199-221, 2004.
[49]X. S. Lou and K. A. Loparo, "Bearing fault diagnosis based on wavelet transform and fuzzy inference," Mechanical Systems and Signal Processing, vol. 18, no. 5, pp. 1077-1095, Sep 2004, doi: 10.1016/s0888-3270(03)00077-3.
[50]F. Jia, Y. Lei, J. Lin, X. Zhou, and N. Lu, "Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data," Mechanical systems and signal processing, vol. 72, pp. 303-315, 2016.
[51]T. Pan, J. Chen, T. Zhang, S. Liu, S. He, and H. Lv, "Generative adversarial network in mechanical fault diagnosis under small sample: A systematic review on applications and future perspectives," ISA transactions, vol. 128, pp. 1-10, 2022.
[52]J. Ho, A. Jain, and P. Abbeel, "Denoising diffusion probabilistic models," Advances in neural information processing systems, vol. 33, pp. 6840-6851, 2020.
[53]N. Araslanov and S. Roth, "Self-supervised augmentation consistency for adapting semantic segmentation," in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 15384-15394.
[54]I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A. Courville, "Improved training of Wasserstein GANs Advances in Neural Information Processing Systems vol 30 ed Guyon I," Luxburg UV, Bengio S, Wallach H, Fergus R, Vishwanathan S and Garnett R (Curran Associates, Inc.) p, vol. 5767, 2017.
[55]D. Verstraete, A. Ferrada, E. L. Droguett, V. Meruane, and M. Modarres, "Deep learning enabled fault diagnosis using time‐frequency image analysis of rolling element bearings," Shock and Vibration, vol. 2017, no. 1, p. 5067651, 2017.
[56]S. Langarica, C. Rüffelmacher, and F. Nunez, "An industrial internet application for real-time fault diagnosis in industrial motors," IEEE Transactions on Automation Science and Engineering, vol. 17, no. 1, pp. 284-295, 2019.
[57]R. Liu, G. Meng, B. Yang, C. Sun, and X. Chen, "Dislocated time series convolutional neural architecture: An intelligent fault diagnosis approach for electric machine," IEEE Transactions on Industrial Informatics, vol. 13, no. 3, pp. 1310-1320, 2016.
[58]J. Gu et al., "Recent advances in convolutional neural networks," Pattern recognition, vol. 77, pp. 354-377, 2018.
[59]V. Nair and G. E. Hinton, "Rectified linear units improve restricted boltzmann machines," in Proceedings of the 27th international conference on machine learning (ICML-10), 2010, pp. 807-814.
[60]P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus, and Y. LeCun, "Overfeat: Integrated recognition, localization and detection using convolutional networks," arXiv preprint arXiv:1312.6229, 2013.
[61]K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770-778.
[62]L. Wan, Y. Li, K. Chen, K. Gong, and C. Li, "A novel deep convolution multi-adversarial domain adaptation model for rolling bearing fault diagnosis," Measurement, vol. 191, p. 110752, 2022.
[63]S. J. Pan and Q. A. Yang, "A Survey on Transfer Learning," Ieee Transactions on Knowledge and Data Engineering, vol. 22, no. 10, pp. 1345-1359, Oct 2010, doi: 10.1109/tkde.2009.191.
[64]J. Yosinski, J. Clune, Y. Bengio, and H. Lipson, "How transferable are features in deep neural networks?," Advances in neural information processing systems, vol. 27, 2014.
[65]K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," arXiv preprint arXiv:1409.1556, 2014.
[66]M. Tan and Q. Le, "Efficientnet: Rethinking model scaling for convolutional neural networks," in International conference on machine learning, 2019: PMLR, pp. 6105-6114.
[67]D. Łuczak, "Mechanical vibrations analysis in direct drive using CWT with complex Morlet wavelet," Power Electronics and Drives, vol. 8, pp. 65-73, 2023.
[68]Z. Dai, L. Zhao, K. Wang, and Y. Zhou, "Mode standardization: A practical countermeasure against mode collapse of GAN-based signal synthesis," Applied Soft Computing, vol. 150, p. 111089, 2024.
[69]L. Yuan, D. Lian, X. Kang, Y. Chen, and K. Zhai, "Rolling bearing fault diagnosis based on convolutional neural network and support vector machine," IEEE Access, vol. 8, pp. 137395-137406, 2020.
[70]Y. Zhang, X. Qin, Y. Han, and Q. Huang, "Vibration amplitude normalization enhanced fault diagnosis under conditions of variable speed and extremely limited samples," Measurement Science and Technology, vol. 34, no. 12, p. 125111, 2023.
[71]B. Noureddine, P. Remus, R. Raphael, and S. Salim, "Rolling bearing failure detection in induction motors using stator current, vibration and stray flux analysis techniques," in IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society, 2020: IEEE, pp. 1088-1095.
[72]A. L. Maas, A. Y. Hannun, and A. Y. Ng, "Rectifier nonlinearities improve neural network acoustic models," in Proc. icml, 2013, vol. 30, no. 1: Atlanta, GA, p. 3.
[73]S. Ioffe and C. Szegedy, "Batch normalization: Accelerating deep network training by reducing internal covariate shift," in International conference on machine learning, 2015: pmlr, pp. 448-456.
[74]N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, "Dropout: a simple way to prevent neural networks from overfitting," The journal of machine learning research, vol. 15, no. 1, pp. 1929-1958, 2014.
[75]D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," arXiv preprint arXiv:1412.6980, 2014.
[76]D. M. Powers, "Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation," arXiv preprint arXiv:2010.16061, 2020.
[77]F. Pedregosa et al., "Scikit-learn: Machine learning in Python," the Journal of machine Learning research, vol. 12, pp. 2825-2830, 2011.
[78]C. Chen, Y. Wang, H. Ruan, Y. Qin, and B. Tang, "A robust intelligent fault diagnosis method for rotating machinery under noisy labels," Measurement Science and Technology, vol. 34, no. 12, p. 125153, 2023.
[79]A. Antoniou, A. Storkey, and H. Edwards, "Data augmentation generative adversarial networks," arXiv preprint arXiv:1711.04340, 2017.
[80]T. Fawcett, "An introduction to ROC analysis," Pattern recognition letters, vol. 27, no. 8, pp. 861-874, 2006.
[81]Y. You, I. Gitman, and B. Ginsburg, "Scaling sgd batch size to 32k for imagenet training," arXiv preprint arXiv:1708.03888, vol. 6, no. 12, p. 6, 2017.
[82]L. Van der Maaten and G. Hinton, "Visualizing data using t-SNE," Journal of machine learning research, vol. 9, no. 11, 2008.
[83]F. Wilcoxon, "Individual comparisons by ranking methods," in Breakthroughs in statistics: Methodology and distribution: Springer, 1992, pp. 196-202.
[84]J. Demšar, "Statistical comparisons of classifiers over multiple data sets," Journal of Machine learning research, vol. 7, no. Jan, pp. 1-30, 2006.
[85]R. Shwartz-Ziv and A. Armon, "Tabular data: Deep learning is not all you need," Information Fusion, vol. 81, pp. 84-90, 2022.
[86]J. A. Hanley and B. J. McNeil, "The meaning and use of the area under a receiver operating characteristic (ROC) curve," Radiology, vol. 143, no. 1, pp. 29-36, 1982.
[87]T. Saito and M. Rehmsmeier, "The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets," PloS one, vol. 10, no. 3, p. e0118432, 2015.
[88]M. Dohmen, M. A. Klemens, I. M. Baltruschat, T. Truong, and M. Lenga, "Similarity and quality metrics for MR image-to-image translation," Scientific Reports, vol. 15, no. 1, p. 3853, 2025.
[89]M. Lucic, K. Kurach, M. Michalski, S. Gelly, and O. Bousquet, "Are gans created equal? a large-scale study," Advances in neural information processing systems, vol. 31, 2018.
[90]T. Salimans, I. Goodfellow, W. Zaremba, V. Cheung, A. Radford, and X. Chen, "Improved techniques for training gans," Advances in neural information processing systems, vol. 29, 2016.
[91]S. Arora and Y. Zhang, "Do gans actually learn the distribution? an empirical study," arXiv preprint arXiv:1706.08224, 2017.
[92]M. Frid-Adar, I. Diamant, E. Klang, M. Amitai, J. Goldberger, and H. Greenspan, "GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification," Neurocomputing, vol. 321, pp. 321-331, 2018.
[93]J. Donahue and K. Simonyan, "Large scale adversarial representation learning," Advances in neural information processing systems, vol. 32, 2019.
[94]M. Mirza and S. Osindero, "Conditional generative adversarial nets," arXiv preprint arXiv:1411.1784, 2014.
[95]M. Buda, A. Maki, and M. A. Mazurowski, "A systematic study of the class imbalance problem in convolutional neural networks," Neural networks, vol. 106, pp. 249-259, 2018.
[96]C. Shorten and T. M. Khoshgoftaar, "A survey on image data augmentation for deep learning," Journal of big data, vol. 6, no. 1, pp. 1-48, 2019.
[97]D. Hendrycks and T. Dietterich, "Benchmarking neural network robustness to common corruptions and perturbations," arXiv preprint arXiv:1903.12261, 2019.
[98]A. Madry, A. Makelov, L. Schmidt, D. Tsipras, and A. Vladu, "Towards deep learning models resistant to adversarial attacks," arXiv preprint arXiv:1706.06083, 2017.
[99]B. Recht, R. Roelofs, L. Schmidt, and V. Shankar, "Do imagenet classifiers generalize to imagenet?," in International conference on machine learning, 2019: PMLR, pp. 5389-5400.
[100]V. Sze, Y.-H. Chen, T.-J. Yang, and J. S. Emer, "Efficient processing of deep neural networks: A tutorial and survey," Proceedings of the IEEE, vol. 105, no. 12, pp. 2295-2329, 2017.
[101]A. G. Howard et al., "Mobilenets: Efficient convolutional neural networks for mobile vision applications," arXiv preprint arXiv:1704.04861, 2017.
[102]R. Geirhos et al., "Shortcut learning in deep neural networks," Nature Machine Intelligence, vol. 2, no. 11, pp. 665-673, 2020.