Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

Local weight coupled network: multi-modal unequal semi-supervised domain adaptation

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Existing semi-supervised domain adaptation (SSDA) approaches on visual classification usually assume that the labelled source data are only collected from single modality. However, since single source data cannot fully show the characteristics of the target data, source domain may be collected from multiple modalities (i.e. RGB and depth modalities). Traditional domain adaptation (DA) task makes an unrealistic scenario, where the label space in the source equals to the label space in the target. However, in real-world scenario, source and target domains may have different label spaces. Thus, the irrelevant categories in the source domain will cause two challenges: negative transfer and imbalanced distribution. In this paper, we design a novel deep SSDA framework in an end-to-end fashion, termed Local Weight Coupled Network (LWCN) for effective knowledge transfer, which aims to take advantage of the multi-modal information in the source domain and tackle the mentioned challenges, simultaneously. Specially, we construct the output layer including classification and regression, where the multi-class classifier and the multi-layer feature extractor can be learned jointly for mutual benefits. Empirical evaluations on five cross-domain benchmarks illustrate the competitive performance of our model with respect to the state-of-the-art, especially under the unequal categories scenario.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Algorithm 1
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Data Availability Statement

The datasets generated during and/or analysed during the current study are available from the corresponding author on reasonable request.

References

  1. Aggarwal K, Mijwil MM, Al-Mistarehi AH et al (2022) Has the future started? The current growth of artificial intelligence, machine learning, and deep learning. Iraqi J Comput Sci Math 3(1):115–123

    Google Scholar 

  2. Cai Z, Long Y, Jing XY et al (2018) Adaptive visual-depth fusion transfer. In: Asian conference on computer vision, pp 56–73

  3. Cai Z, Long Y, Shao L (2018) Adaptive rgb image recognition by visual-depth embedding. IEEE Trans Image Process 27(5):2471–2483

    Article  MathSciNet  Google Scholar 

  4. Cai Z, Jing XY, Shao L (2020) Visual-depth matching network: deep rgb-d domain adaptation with unequal categories. IEEE Trans Cybern 52 (6):4623–4635

    Article  Google Scholar 

  5. Cao Z, Long M, Wang J et al (2018) Partial transfer learning with selective adversarial networks. In: IEEE Conference on computer vision and pattern recognition, pp 2724–2732

  6. Cao Z, You K, Long M et al (2019) Learning to transfer examples for partial domain adaptation. In: IEEE Conference on computer vision and pattern recognition, pp 2985–2994

  7. Demšar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1–30

    MathSciNet  Google Scholar 

  8. Deng J, Dong W, Socher R et al (2009) Imagenet: a large-scale hierarchical image database. In: IEEE Conference on computer vision and pattern recognition, pp 248–255

  9. Ding Z, Nasrabadi NM, Fu Y (2018) Semi-supervised deep domain adaptation via coupled neural networks. IEEE Trans Image Process 27(11):5214–5224

    Article  MathSciNet  Google Scholar 

  10. Donahue J, Jia Y, Vinyals O et al (2014) Decaf: a deep convolutional activation feature for generic visual recognition. In: International Conference on machine learning, pp 647–655

  11. Fei-Fei L, Perona P (2005) A bayesian hierarchical model for learning natural scene categories. In: IEEE Conference on computer vision and pattern recognition, pp 524–531

  12. Ganin Y, Ustinova E, Ajakan H et al (2016) Domain-adversarial training of neural networks. J Mach Learn Res 17(1):2096–2030

    MathSciNet  Google Scholar 

  13. Griffin G, Holub A, Perona P (2007) Caltech-256 object category dataset

  14. Gupta S, Girshick R, Arbeláez P et al (2014) Learning rich features from RGB-D images for object detection and segmentation. In: European conference on computer vision, pp 345–360

  15. He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition, pp 770–778

  16. Izonin I, Tkachenko R, Shakhovska N et al (2022) A two-step data normalization approach for improving classification accuracy in the medical diagnosis domain. Mathematics 10(11):1942

    Article  Google Scholar 

  17. Jangra M, Dhull SK, Singh KK et al (2021) O-wcnn: an optimized integration of spatial and spectral feature map for arrhythmia classification. Complex Intell Syst, 1–14

  18. Janoch A, Karayev S, Jia Y et al (2013) A category-level 3D object dataset: putting the kinect to work

  19. Koppanati RK, Kumar K (2020) P-mec: polynomial congruence-based multimedia encryption technique over cloud. IEEE Consum Electron Mag 10(5):41–46

    Article  Google Scholar 

  20. Kumar K (2021) Text query based summarized event searching interface system using deep learning over cloud. Multimed Tools Applic 80(7):11,079–11,094

    Article  Google Scholar 

  21. Kumar K, Shrimankar DD (2017) F-des: fast and deep event summarization. IEEE Trans Multimed 20(2):323–334

    Article  Google Scholar 

  22. Kumar K, Shrimankar DD (2018) Deep event learning boost-up approach: delta. Multimed Tools Applic 77:26,635–26,655

    Article  Google Scholar 

  23. Kumar K, Shrimankar DD, Singh N (2016) Equal partition based clustering approach for event summarization in videos. In: International conference on signal-image technology & internet-based systems, pp 119–126

  24. Kumar K, Shrimankar DD, Singh N (2017) Event bagging: a novel event summarization approach in multiview surveillance videos. In: International conference on innovations in electronics, signal processing and communication, pp 106–111

  25. Kumar K, Shrimankar DD, Singh N (2018) Eratosthenes sieve based key-frame extraction technique for event summarization in videos. Multimed Tools Appl 77:7383–7404

    Article  Google Scholar 

  26. Kumar K, Shrimankar DD, Singh N (2018) Somes: an efficient som technique for event summarization in multi-view surveillance videos. In: Recent findings in intelligent computing techniques, pp 383–389

  27. Lai K, Bo L, Ren X et al (2011) A large-scale hierarchical multi-view RGB-D object dataset. In: IEEE International conference on robotics and automation, pp 1817–1824

  28. Li L, Zhang Z (2018) Semi-supervised domain adaptation by covariance matching. IEEE Trans Pattern Anal Mach Intell 41(11):2724–2739

    Article  Google Scholar 

  29. Li W, Gu J, Dong Y et al (2020) Indoor scene understanding via RGB-D image segmentation employing depth-based CNN and crfs. Multimed Tools Applic 79(47):35,475–35,489

    Article  Google Scholar 

  30. Li Y, Li H, Gao G (2022) Towards end-to-end container code recognition. Multimed Tools Applic 81(11):15,901–15,918

    Article  Google Scholar 

  31. Long M, Zhu H, Wang J et al (2016) Unsupervised domain adaptation with residual transfer networks. In: Advances in neural information processing systems, pp 136–144

  32. Ma N, Bu J, Lu L et al (2022) Context-guided entropy minimization for semi-supervised domain adaptation. Neural Netw 154:270–282

    Article  Google Scholar 

  33. Mancini M, Porzi L, Rota Bulò S et al (2018) Boosting domain adaptation by discovering latent domains. In: IEEE Conference on computer vision and pattern recognition, pp 3771–3780

  34. Park GY, Lee SW (2021) Information-theoretic regularization for multi-source domain adaptation. In: IEEE/CVF International conference on computer vision, pp 9214–9223

  35. Saito K, Kim D, Sclaroff S et al (2019) Semi-supervised domain adaptation via minimax entropy. In: IEEE International conference on computer vision, pp 8050–8058

  36. Shao L, Cai Z, Liu L et al (2017) Performance evaluation of deep feature learning for RGB-D image/video classification. Inform Sci 385:266–283

    Article  Google Scholar 

  37. Shi J, Malik J (2000) Normalized cuts and image segmentation. IEEE Trans Pattern Anal Mach Intell 22:8

    Google Scholar 

  38. Silberman N, Fergus R (2011) Indoor scene segmentation using a structured light sensor. In: IEEE International Conference on Computer Vision Workshops, pp 601–608

  39. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:14091556

  40. Tzeng E, Hoffman J, Saenko K et al (2017) Adversarial discriminative domain adaptation. In: IEEE Conference on computer vision and pattern recognition, pp 7167–7176

  41. Wang Q, Fink O, Van Gool L et al (2022) Continual test-time domain adaptation. In: IEEE/CVF Conference on computer vision and pattern recognition, pp 7201–7211

  42. Wu F, Wei P, Gao G et al (2022) Dual-aligned unsupervised domain adaptation with graph convolutional networks. Multimed Tools Applic 81 (11):14,979–14,997

    Article  Google Scholar 

  43. Xiao J, Jing L, Zhang L et al (2022) Learning from temporal gradient for semi-supervised action recognition. In: IEEE/CVF Conference on computer vision and pattern recognition, pp 3252–3262

  44. Yang C, Cheung YM, Ding J et al (2022) Contrastive learning assisted-alignment for partial domain adaptation. IEEE Transactions on Neural Networks and Learning Systems

  45. Yang N, Zhang C, Zhang Y et al (2022) A benchmark dataset and baseline model for co-salient object detection within rgb-d images. Multimed Tools Applic 81(25):35,831–35,842

    Article  Google Scholar 

  46. Yao S, Kang Q, Zhou M et al (2022) Discriminative manifold distribution alignment for domain adaptation. IEEE Transactions on Systems, Man, and Cybernetics: Systems

  47. Zhou B, Lapedriza A, Xiao J et al (2014) Learning deep features for scene recognition using places database. In: Advances in neural information processing systems, pp 487–495

  48. Zou W, Peng Y, Zhang Z et al (2022) Rgb-d gate-guided edge distillation for indoor semantic segmentation. Multimed Tools Applic 81(25):35,815–35,830

    Article  Google Scholar 

Download references

Acknowledgments

This work is partly supported by the Natural Science Foundation of China (Grant No. 62006127, 62073173, 62176069, 61833011, 62272240 and 62001247), partly supported by Postdoctoral Science Foundation of Jiangsu Grant 2021K290B, and Natural Science Foundation of Guangdong Province under Grant No. 2019A1515011076. It is also supported by Postdoctoral Science Foundation of China (Grant No. 2021M691656).

Author information

Authors and Affiliations

  1. College of Automation, Nanjing University of Posts and Telecommunications, Nanjing, China

    Ziyun Cai, Jie Song, Tengfei Zhang & Changhui Hu

  2. School of Computer, Guangdong University of Petrochemical Technology, Maoming, China

    Xiao-Yuan Jing

  3. State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China

    Xiao-Yuan Jing

Authors
  1. Ziyun Cai
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jie Song
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tengfei Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Changhui Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xiao-Yuan Jing
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ziyun Cai.

Ethics declarations

Conflict of Interests

The authors declare that they have no conflict of interest.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Cai, Z., Song, J., Zhang, T. et al. Local weight coupled network: multi-modal unequal semi-supervised domain adaptation. Multimed Tools Appl 83, 4331–4357 (2024). https://doi.org/10.1007/s11042-023-15439-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-023-15439-1

Keywords

Search

Navigation