2023 Vol.6 Dec.N06

• Title: Unsupervised Manifold Adversarial Domain Adaptation Network for Tumor image diagnosis
• Name: Shunmin Wang1,2, Qingyu Peng3*, Bo Zhou1,2, Tingting Yang1,2, Fu
• Company: 1School of Information & Intelligence Engineering, University of Sanya, Sanya, 572022, China 2Academician Guoliang Chen Team Innovation Center, University of Sanya, Sanya, 572022, China 3School of computer science and technology, Hainan Tropical Ocean Uni
• Abstract:

  When there are no labeled samples or few labeled samples, the model constructed by machine learning is prone to over fitting, poor expression ability and poor generalization. Domain adaptation can realize the adaptation from rich label source domain to unlabeled target domain, which is the inevitable choice to solve the above problems. In this paper, a unsupervised manifold adversarial domain adaptation network is proposed. Firstly, the pre-trained model of the source domain data is used as the initialization parameter of the model, and then the domain differences between the target domain and the source domain are effectively reduced through the competition between the discriminator and the feature extractor. Embedding manifold learning can effectively reduce the intra-class differences, so that the distance between the data of the same category is gradually reduced to further data alignment, this assist the process of adversarial learning and play the role of adversarial learning in a greater extent. The simulation results on tumor data set show the effectiveness of the method, which to some extent reduces the cost of hardware resources.

  
  

• Keyword: Domain adaptation; Adversarial learning; Unsupervised learning; Manifold alignment; Transfer learning.
• DOI: 10.12250/jpciams2023090814
• Citation form: Shunmin Wang.Unsupervised Manifold Adversarial Domain Adaptation Network for Tumor image diagnosis [J]. Computer Informatization and Mechanical System,2023,Vol.6,pp.65-70

References

[1] L. Wang and A. Wong. Covid-net: A tailored deep convolutional neural network design for detection of covid-19 cases from chest radiography images [J]. ArXiv, 2020.

[2] He C, Zheng L, Tan T, et al.Manifold discrimination partial adversarial domain adaptation[J].Knowledge-based systems, 2022.

[3] Jing Zhang, Wanqing Li, Philip Ogunbona, et al. Recent Advances in Transfer Learning for Cross-Dataset Visual Recognition: A Problem-Oriented Perspective [J]. ArXiv, 2019.

[4] L. Zhang. Transfer Adaptation Learning: A Decade Survey [C]. Conference on Computer Vision and Pattern Recognition, 2019, 1903-4687.

[5] Chunmei He*, Shunming Wang, Hongyu Kang, Lanqing Zheng, Xianjun Fan, Taifeng Tan. Adversarial Domain Adaptation Network for Tumor image diagnosis. International Journal of Approximate Reasoning, 2021, 135:38-52.

[6] Tzeng, E., Hoffman, J., Zhang, et al. Deep domain confusion:Maximizing for domain invariance [J]. Computing Research Repository, 2014.

[7] Zellinger W, Grubinger T, Lughofer, E, et al. Central moment discrepancy (CMD) for domain-invariant representation learning [C]. International Conference on Learning Representations, 2017.

[8] Y. Ganin and V. Lempitsky. Unsupervised domain adaptation by backpropagation [J], ArXiv, 2014.

[9] J. Zhang, Z. Ding, W. Li and P. Ogunbona. Importance Weighted Adversarial Nets for Partial Domain Adaptation [C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, 8156-8164.

[10] S. Motamed and F. Khalvati, "Multi-class Generative Adversarial Networks: Improving One-class Classification of Pneumonia Using Limited Labeled Data," 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Mexico, 2021, pp. 3817-3822.

[11] E. Tzeng, J. Hoffman, K. Saenko and T. Darrell. Adversarial Discriminative Domain Adaptation [C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017, 2962-2971.

[12] He C , Tan T , Fan X ,et al. Noise-residual Mixup for unsupervised adversarial domain adaptation[J]. Applied Intelligence, 2023, 53(3):3034-3047. 

[13] C. Chen, Q. Dou, H. Chen, J. Qin and P. A. Heng, "Unsupervised Bidirectional Cross-Modality Adaptation via Deeply Synergistic Image and Feature Alignment for Medical Image Segmentation," in IEEE Transactions on Medical Imaging, vol. 39, no. 7, pp. 2494-2505, July 2020.

[14] I. Goodfellow, J. Pouget-Abadie, M. Mirza, et al. Generative adversarial nets [J], Advances in Neural Information Processing Systems, 2014.

[15] L. Hu, M. Kan, S. Shan, and X. Chen. Duplex Generative Adversarial Network for Unsupervised Domain Adaptation [C]. Conference on Computer Vision and Pattern Recognition, 2018, 498-1507.

[16] W. Hong, Z. Wang, M. Yang, and J. Yuan, Conditional generative adversarial network for structured domain adaptation, [C]. Conference on Computer Vision and Pattern Recognition, 2018, 1498-1507.

[17] Xing F, Cornish T C, Bennett T D, et al. Bidirectional mapping-based domain adaptation for nucleus detection in cross-modality microscopy images[J]. IEEE Transactions on Medical Imaging, 2020, 40(10): 2880-2896.

[18] Suzuki K, Zhou L P, Wang Q. Machine learning in medical imaging [J]. Pattern Recognition, 2017, 63: 465-467.

[19] Tian Juanxiu, Liu Guocai, et al. Research and Challenges in Deep Learning Methods for Medical Image Analysis [J] Journal of Automation, 2018, 44 (3): 401-424.

[20] Zhang Peng, Xu Xinnan, et al. A Computer Aided Lung Cancer Diagnosis Method Based on Deep Learning [J] Journal of Computer Aided Design and Graphics, 2018, 30 (01): 90-99.

[21] Chougrad H, Zouaki H, Alheyane O. Deep Convolutional Neural Networks for Breast Cancer Screening [J]. Computer Methods & Programs in Biomedicine, 2018, 157:19-30.

[22] Liang Cuixia, Li Mingqiang, et al. Evaluation of breast tumor classification models based on deep learning features [J] Journal of Southern Medical University, 2019 (01): 88-92.

[23] Y. W. Luo, C. X. Ren, D. Q. DAI and H. Yan. Unsupervised Domain Adaptation via Discriminative Manifold Propagation [C]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020.

[24] Spanhol F. A, Oliveira L. S, Petitjean C, et al. A Dataset for Breast Cancer Histopathological Image Classification[J]. IEEE transactions on bio-medical engineering, 2016, 63(7):1455-1462.

[25] K Simonyan, A. Zisserman, Simonyan K, et al. Very Deep Convolutional Networks for Large-Scale Image Recognition[J]. Computer Science, 2014.

[26] Ganin Y, Ustinova E, Ajakan H, et al. Domain-Adversarial Training of Neural Networks [J]. Journal of Machine Learning Research, 2017, 17(1):2096-2030.

[27] Tzeng E, Hoffman J, Zhang Ning, et al. Deep Domain Confusion: Maximizing for Domain Invariance[J]. arXiv, 2014.

[28] M. Long, Y. Cao, Z. Cao, et al. Transferable representation learning with deep adaptation networks[C]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8)1798-1828.