A journal of IEEE and CAA , publishes high-quality papers in English on original theoretical/experimental research and development in all areas of automation
Advanced Search

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 19.2, Top 1 (SCI Q1)
    CiteScore: 28.2, Top 1% (Q1)
    Google Scholar h5-index: 95， TOP 5
Turn off MathJax
Article Contents
Article Navigation >  IEEE/CAA Journal of Automatica Sinica  > 2026  > In Press, Accepted Manuscript
W. Mao, J. Wu, S. Du, K. Feng, and Z. Wang, “Collaboration better than integration: A novel time-frequency-assisted deep feature enhancement mechanism for few-shot transfer learning in anomaly detection,” IEEE/CAA J. Autom. Sinica, vol. 13, no. 2, pp. 1–17, Feb. 2026. doi: 10.1109/JAS.2025.125702
Citation: W. Mao, J. Wu, S. Du, K. Feng, and Z. Wang, “Collaboration better than integration: A novel time-frequency-assisted deep feature enhancement mechanism for few-shot transfer learning in anomaly detection,” IEEE/CAA J. Autom. Sinica, vol. 13, no. 2, pp. 1–17, Feb. 2026. doi: 10.1109/JAS.2025.125702
shu

Collaboration Better Than Integration: A Novel Time-Frequency-Assisted Deep Feature Enhancement Mechanism for Few-Shot Transfer Learning in Anomaly Detection

doi: 10.1109/JAS.2025.125702
Funds:  This work was supported in part by the National Natural Science Foundation of China (62472146) and the Key Technologies Research Development Joint Foundation of Henan Province of China (225101610001)
More Information
    Abstract
  • Deep transfer learning has achieved significant success in anomaly detection over the past decade, but data acquisition challenges in practical engineering hinder high-quality feature representation for few-shot learning tasks. To address this issue, a novel time-frequency-assisted deep feature enhancement (TFE) mechanism is proposed. Unlike traditional methods that integrate time-frequency analysis with deep neural networks, TFE employs a wavelet scattering transform to establish a parallel time-frequency feature space, where a dual interaction strategy facilitates collaboration between deep feature and time-frequency spaces through two operations: 1) Enhancement, where a frequency-importance-driven contrastive learning (FICL) network transfers physically-aware information from wavelet scattering features to deep features, and 2) Feedback, which uses a detection rule adaptation module to minimize bias in wavelet scattering features based on deep feature performance. TFE is applied to a domain-adversarial anomaly detection framework and, through alternating training, significantly enhances both deep feature discriminative power and few-shot anomaly detection. Theoretical analysis confirms that the proposed dual interaction strategy reduces the upper bound of classification error. Experiments on benchmark datasets and a real-world industrial dataset from a large steel factory demonstrate TFE’s superior performance and highlight the importance of frequency saliency in transfer learning. Thus, collaboration is shown to outperform integration for few-shot transfer learning in anomaly detection.

     

    • FullText(HTML)
  • loading
    • References(66)
  • [1]
    A. F. Laine, S. Schuler, J. Fan, and W. Huda, “Mammographic feature enhancement by multiscale analysis,” IEEE Trans. Med. Imaging, vol. 13, no. 4, pp. 725–740, Dec. 1994. doi: 10.1109/42.363095
    [2]
    F. H. K. dos Santos Tanaka and C. Aranha, “Data augmentation using GANs,” arXiv preprint arXiv: 1904.09135, 2019.
    [3]
    X. Chen, L. Zeng, M. Gao, C. Ding, and Y. Bian, “DiffWT: Diffusion-based pedestrian trajectory prediction with time-frequency wavelet transform,” IEEE Internet Things J., vol. 12, no. 5, pp. 5109–5121, Mar. 2025. doi: 10.1109/JIOT.2024.3489638
    [4]
    L. Jia, T. W. S. Chow, and Y. Yuan, “GTFE-Net: A gramian time frequency enhancement CNN for bearing fault diagnosis,” Eng. Appl. Artif. Intell., vol. 119, p. 105794, Mar. 2023. doi: 10.1016/j.engappai.2022.105794
    [5]
    S. Zhang, Z. Tao, and S. Lin, “WaveletFormerNet: A transformer-based wavelet network for real-world non-homogeneous and dense fog removal,” Image Vision Comput., vol. 146, p. 105014, Jun. 2024. doi: 10.1016/j.imavis.2024.105014
    [6]
    J. Shi, Y. Zhao, W. Xiang, V. Monga, X. Liu, and R. Tao, “Deep scattering network with fractional wavelet transform,” IEEE Trans. Signal Process., vol. 69, pp. 4740–4757, Oct. 2021. doi: 10.1109/TSP.2021.3098936
    [7]
    Y. Chen, Z. Zhao, H. Wu, X. Chen, Q. Xiao, and Y. Yu, “Fault anomaly detection of synchronous machine winding based on isolation forest and impulse frequency response analysis,” Measurement, vol. 188, p. 110531, Jan. 2022. doi: 10.1016/j.measurement.2021.110531
    [8]
    J. Saari, D. Strömbergsson, J. Lundberg, and A. Thomson, “Detection and identification of windmill bearing faults using a one-class support vector machine (SVM),” Measurement, vol. 137, pp. 287–301, Apr. 2019. doi: 10.1016/j.measurement.2019.01.020
    [9]
    Y. Zhao, S. Wang, and F. Xiao, “Pattern recognition-based chillers fault detection method using support vector data description (SVDD),” Appl. Energy, vol. 112, pp. 1041–1048, Dec. 2013. doi: 10.1016/j.apenergy.2012.12.043
    [10]
    X. Li, M. Li, P. Yan, G. Li, Y. Jiang, H. Luo and S. Yin, “Deep learning attention mechanism in medical image analysis: Basics and beyonds,” Int. J. Netw. Dyn. Intell., vol. 2, no. 1, pp. 93–116, Mar. 2023.
    [11]
    C. Ma, P. Cheng, and C. Cai, “Localization and mapping method based on multimodal information fusion and deep learning for dynamic object removal,” Int. J. Netw. Dyn. Intell., vol. 3, no. 2, p. 100008, Jun. 2024.
    [12]
    D. Wang, C. Wen, and X. Feng, “Deep variational Luenberger-type observer with dynamic objects channel-attention for stochastic video prediction,” Int. J. Syst. Sci., vol. 55, no. 4, pp. 728–740, Dec. 2024. doi: 10.1080/00207721.2023.2293686
    [13]
    J. Wang, Y. Zhuang, and Y. Liu, “FSS-Net: A fast search structure for 3D point clouds in deep learning,” Int. J. Netw. Dyn. Intell., vol. 2, no. 2, p. 100005, Jun. 2023.
    [14]
    L. Ruff, R. Vandermeulen, N. Goernitz, L. Deecke, S. A. Siddiqui, A. Binder, E. Müller, and M. Kloft, “Deep one-class classification,” in Proc. 35th Int. Conf. Machine Learning, Stockholm, Sweden, 2018, pp. 4393−4402.
    [15]
    S. Baireddy, S. R. Desai, J. L. Mathieson, R. H. Foster, M. W. Chan, and M. L. Comer, “Spacecraft time-series anomaly detection using transfer learning,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Nashville, USA, 2021, pp. 1951−1960.
    [16]
    P. Bergmann, M. Fauser, D. Sattlegger, and C. Steger, “Uninformed students: Student-teacher anomaly detection with discriminative latent embeddings,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Seattle, USA, 2020, pp. 4182−4191.
    [17]
    H. Han, H. Liu, C. Yang, and J. Qiao, “Transfer learning algorithm with knowledge division level,” IEEE Trans. Neural Netw. Learn. Syst., vol. 34, no. 11, pp. 8602–8616, Nov. 2023. doi: 10.1109/TNNLS.2022.3151646
    [18]
    M. Subramanian, K. Shanmugavadivel, and P. S. Nandhini, “On fine-tuning deep learning models using transfer learning and hyper-parameters optimization for disease identification in maize leaves,” Neural Comput. Appl., vol. 34, no. 16, pp. 13951–13968, Aug. 2022. doi: 10.1007/s00521-022-07246-w
    [19]
    Z. N. K. Swati, Q. Zhao, M. Kabir, F. Ali, Z. Ali, S. Ahmed, and J. Lu, “Brain tumor classification for MR images using transfer learning and fine-tuning,” Comput. Med. Imaging Graph., vol. 75, pp. 34–46, Jul. 2019. doi: 10.1016/j.compmedimag.2019.05.001
    [20]
    Y. Zhou, X. Liang, W. Zhang, L. Zhang, and X. Song, “VAE-based deep SVDD for anomaly detection,” Neurocomputing, vol. 453, pp. 131–140, Sept. 2021. doi: 10.1016/j.neucom.2021.04.089
    [21]
    H. S. Farahani, A. Fatehi, A. Nadali, and M. A. Shoorehdeli, “Domain Adversarial Neural Network Regression to design transferable soft sensor in a power plant,” Comput. Ind., vol. 132, p. 103489, Nov. 2021. doi: 10.1016/j.compind.2021.103489
    [22]
    X. Han and S. Yuan, “Unsupervised cross-system log anomaly detection via domain adaptation,” in Proc. 30th ACM Int. Conf. Information and Knowledge Management, Queensland, Australia, 2021, pp. 3068−3072.
    [23]
    G. Ma, Z. Wang, W. Liu, J. Fang, Y. Zhang, H. Ding, and Y. Yuan, “Estimating the state of health for lithium-ion batteries: A particle swarm optimization-assisted deep domain adaptation approach,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 7, pp. 1530–1543, Jul. 2023. doi: 10.1109/JAS.2023.123531
    [24]
    M. Ragab, E. Eldele, Z. Chen, M. Wu, C.-K. Kwoh, and X. Li, “Self-supervised autoregressive domain adaptation for time series data,” IEEE Trans. Neural Netw. Learn. Syst., vol. 35, no. 1, pp. 1341–1351, Jan. 2024. doi: 10.1109/TNNLS.2022.3183252
    [25]
    T. Shermin, G. Lu, S. W. Teng, M. Murshed, and F. Sohel, “Adversarial network with multiple classifiers for open set domain adaptation,” IEEE Trans. Multimed., vol. 23, pp. 2732–2744, 2021. doi: 10.1109/TMM.2020.3016126
    [26]
    C. Wang, Z. Wang, W. Liu, Y. Shen and H. Dong, “A novel deep offline-to-online transfer learning framework for pipeline leakage detection with small samples,” IEEE Trans. Instrum. Meas., vol. 72, p. 3503913, Jan. 2023.
    [27]
    Z. Yang, I. Soltani, and E. Darve, “Anomaly detection with domain adaptation,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Vancouver, BC, Canada, 2023, pp. 2958−2967.
    [28]
    W. Mao, G. Wang, L. Kou, and X. Liang, “Deep domain-adversarial anomaly detection with one-class transfer learning,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 2, pp. 524–546, Feb. 2023. doi: 10.1109/JAS.2023.123228
    [29]
    C. Bowles, L. Chen, R. Guerrero, P. Bentley, R. Gunn, A. Hammers, D. A. Dickie, M. Valdés Hernández, J. Wardlaw, and D. Rueckert , “GAN augmentation: Augmenting training data using generative adversarial networks,” arXiv preprint arXiv: 1810.10863, 2018.
    [30]
    M. Frid-Adar, E. Klang, M. Amitai, J. Goldberger, and H. Greenspan, “Synthetic data augmentation using GAN for improved liver lesion classification,” in Proc. 15th Int. Symp. on Biomedical Imaging, Washington, USA, 2018, pp. 289−293.
    [31]
    I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial networks,” Commun. ACM, vol. 63, no. 11, pp. 139–144, Oct. 2020. doi: 10.1145/3422622
    [32]
    M. Kang, J. Shin, and J. Park, “StudioGAN: A taxonomy and benchmark of GANs for image synthesis,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 12, pp. 15725–15742, Dec. 2023. doi: 10.1109/TPAMI.2023.3306436
    [33]
    K. Liu, Z. Ye, H. Guo, D. Cao, L. Chen, and F.-Y. Wang, “FISS GAN: A generative adversarial network for foggy image semantic segmentation,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 8, pp. 1428–1439, Aug. 2021. doi: 10.1109/JAS.2021.1004057
    [34]
    N.-T. Tran, V.-H. Tran, N.-B. Nguyen, T.-K. Nguyen, and N.-M. Cheung, “On data augmentation for GAN training,” IEEE Trans. Image Process., vol. 30, pp. 1882–1897, Jan. 2021. doi: 10.1109/TIP.2021.3049346
    [35]
    J. Ho, A. Jain, and P. Abbeel, “Denoising diffusion probabilistic models,” in Proc. 34th Int. Conf. Neural Information Processing Systems, Vancouver, Canada, 2020, pp. 574.
    [36]
    Y. Fu, X. Xie, Y. Fu, J. Chen, and Y.-G. Jiang, “Wave-SAN: Wavelet based style augmentation network for cross-domain few-shot learning,” arXiv preprint arXiv: 2203.07656, 2022.
    [37]
    M. Behmanesh, P. Adibi, S. Ehsani, and J. Chanussot, “Geometric multimodal deep learning with multiscaled graph wavelet convolutional network,” IEEE Trans. Neural Netw. Learn. Syst., vol. 35, no. 5, pp. 6991–7005, May 2022.
    [38]
    L. El Bouny, M. Khalil, and A. Adib, “ECG heartbeat classification based on multi-scale wavelet convolutional neural networks,” in Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing, Barcelona, Spain, 2020, pp. 3212−3216.
    [39]
    X. Fu, J. Tao, K. Jiao, and C. Liu, “A novel semi-supervised prototype network with two-stream wavelet scattering convolutional encoder for TBM main bearing few-shot fault diagnosis,” Knowl.-Based Syst., vol. 286, p. 111408, Feb. 2024. doi: 10.1016/j.knosys.2024.111408
    [40]
    M. Mishra, P. B. Dash, J. Nayak, B. Naik, and S. K. Swain, “Deep learning and wavelet transform integrated approach for short-term solar PV power prediction,” Measurement, vol. 166, p. 108250, Dec. 2020. doi: 10.1016/j.measurement.2020.108250
    [41]
    E. Pan, Y. Ma, X. Mei, J. Huang, F. Fan, and J. Ma, “D2Net: Deep denoising network in frequency domain for hyperspectral image,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 3, pp. 813–815, Mar. 2023. doi: 10.1109/JAS.2022.106019
    [42]
    A. Tirinzoni, A. Sessa, M Pirotta, and M. Restelli, “Importance weighted transfer of samples in reinforcement learning,” in Proc. 35th Int. Conf. Machine Learning, Stockholm, Sweden, 2018, pp. 4936−4945.
    [43]
    J. Zhang, Z. Ding, W. Li, and P. Ogunbona, “Importance weighted adversarial nets for partial domain adaptation,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 8156−8164.
    [44]
    P. Bugata and P. Drotár, “Feature selection based on a sparse neural-network layer with normalizing constraints,” IEEE Trans. Cybern., vol. 53, no. 1, pp. 161–172, Jan. 2023. doi: 10.1109/TCYB.2021.3087776
    [45]
    A. Jeyasothy, S. Suresh, S. Ramasamy, and N. Sundararajan, “Development of a novel transformation of spiking neural classifier to an interpretable classifier,” IEEE Trans. Cybern., vol. 54, no. 1, pp. 3–12, Jan. 2024. doi: 10.1109/TCYB.2022.3181181
    [46]
    J. Wu, W. Mao, Y. Zhang, L. Fan, and Z. Zhong, “A novel few-shot deep transfer learning method for anomaly detection: Deep domain-adversarial contrastive network with time-frequency transferability analytics,” IEEE Internet Things J., vol. 11, no. 17, pp. 28809–28823, Sept. 2024. doi: 10.1109/JIOT.2024.3403976
    [47]
    Y. Dhebar and K. Deb, “Interpretable rule discovery through bilevel optimization of split-rules of nonlinear decision trees for classification problems,” IEEE Trans. Cybern., vol. 51, no. 11, pp. 5573–5584, Nov. 2021. doi: 10.1109/TCYB.2020.3033003
    [48]
    C. Singh, W. J. Murdoch, and B. Yu, “Hierarchical interpretations for neural network predictions,” in Proc. 7th Int. Conf. Learning Representations, New Orleans, LA, USA, 2019.
    [49]
    M. D. Zeiler and R. Fergus, “Visualizing and understanding convolutional networks,” in Proc. 13th European Conf. Computer Vision, Zurich, Switzerland, 2014, pp. 818−833.
    [50]
    C. N. Nguyen, P. Tran, L. S. T. Ho, V. Dinh, A. T. Tran, T. Hassner, and C. V. Nguyen, “Transferability between regression tasks,” in Proc. 36th Conf. Neural Information Processing Systems, 2022.
    [51]
    Y. Xue, R. Yang, X. Chen, W. Liu, Z. Wang, and X. Liu, “A review on transferability estimation in deep transfer learning,” IEEE Trans. Artif. Intell., vol. 5, no. 12, pp. 5894–5914, Dec. 2024. doi: 10.1109/TAI.2024.3445892
    [52]
    J.-B. Grill, F. Strub, F. Altché, C. Tallec, P. H. Richemond, E. Buchatskaya, et al., “Bootstrap your own latent a new approach to self-supervised learning,” in Proc. 34th Int. Conf. Neural Information Processing Systems, Vancouver, Canada, 2020, pp. 1786.
    [53]
    K. He and J. Sun, “Convolutional neural networks at constrained time cost,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Boston, USA, 2015, pp. 5353−5360.
    [54]
    W. Huang, M. Yi, X. Zhao, and Z. Jiang, “Towards the generalization of contrastive self-supervised learning,” in Proc. 11th Int. Conf. Learning Representations, Kigali, Rwanda, 2023.
    [55]
    G. Pang, C. Shen, L. Cao, and A. Van Den Hengel, “Deep learning for anomaly detection: A review,” ACM Comput. Surv., vol. 54, no. 2, p. 38, Mar. 2021.
    [56]
    K. Sohn, C.-L. Li, J. Yoon, M. Jin, and T. Pfister, “Learning and evaluating representations for deep one-class classification,” in Proc. 9th Int. Conf. Learning Representations, 2021.
    [57]
    H. Venkateswara, J. Eusebio, S. Chakraborty, and S. Panchanathan, “Deep hashing network for unsupervised domain adaptation,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Honolulu, HI, USA, 2017, pp. 5385−5394.
    [58]
    P. Nectoux, R. Gouriveau, K. Medjaher, E. Ramasso, B. Chebel-Morello, N. Zerhouni, and C. Varnier, “PRONOSTIA: An experimental platform for bearings accelerated degradation tests,” in Proc. IEEE Int. Conf. Prognostics and Health Management, 2012, pp. 1−8.
    [59]
    W. Mao, L. Ding, S. Tian, and X. Liang, “Online detection for bearing incipient fault based on deep transfer learning,” Measurement, vol. 152, p. 107278, Feb. 2020. doi: 10.1016/j.measurement.2019.107278
    [60]
    Y. Li, M. Xu, X. Liang, and W. Huang, “Application of bandwidth EMD and adaptive multiscale morphology analysis for incipient fault diagnosis of rolling bearings,” IEEE Trans. Ind. Electron., vol. 64, no. 8, pp. 6506–6517, Aug. 2017. doi: 10.1109/TIE.2017.2650873
    [61]
    T. Reiss, N. Cohen, L. Bergman, and Y. Hoshen, “PANDA: Adapting pretrained features for anomaly detection and segmentation,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Nashville, TN, USA, 2021, pp. 2805−2812.
    [62]
    W. Mao, J. Chen, X. Liang, and X. Zhang, “A new online detection approach for rolling bearing incipient fault via self-adaptive deep feature matching,” IEEE Trans. Instrum. Meas., vol. 69, no. 2, pp. 443–456, Feb. 2020. doi: 10.1109/TIM.2019.2903699
    [63]
    W. Lu, Y. Li, Y. Cheng, D. Meng, B. Liang, and P. Zhou, “Early fault detection approach with deep architectures,” IEEE Trans. Instrum. Meas., vol. 67, no. 7, pp. 1679–1689, Jul. 2018. doi: 10.1109/TIM.2018.2800978
    [64]
    X.-P. Guo, S.-Y. Liu, and Y. Li, “Fault detection of multi-mode processes employing sparse residual distance,” Acta Autom. Sinica, vol. 45, no. 3, pp. 617–625, Mar. 2019.
    [65]
    W. Lu, B. Liang, Y. Cheng, D. Meng, J. Yang, and T. Zhang, “Deep model based domain adaptation for fault diagnosis,” IEEE Trans. Ind. Electron., vol. 64, no. 3, pp. 2296–2305, Mar. 2017. doi: 10.1109/TIE.2016.2627020
    [66]
    S. Mallat, “Group invariant scattering,” Commun. Pure Appl. Math., vol. 65, no. 10, pp. 1331–1398, Oct. 2012. doi: 10.1002/cpa.21413
    • Related Articles
    • Supplements(0)

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(17)  / Tables(4)

    Get Citation
    PDF
    XML

    Article Metrics

    Article views (28) PDF downloads(6) Cited by()

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return