Skip to main content
SpringerLink
Log in

BiLSTM-TANet: an adaptive diverse scenes model with context embeddings for few-shot learning

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Few-shot learning is a critical task in computer vision processing that helps reduce deep learning’s reliance on large datasets. This paper aims to establish a few-shot learning network that is adaptive to diverse scenes. A novel approach referred to as task-adapted network with bi-directional long short-term memory network (BiLSTM-TANet) is proposed in this paper. BiLSTM-TANet is an end-to-end approach based on deep metric learning and designed to use the information from finite samples as much as possible. It fuses the context embeddings and structure information of the images and adaptively adjusts the features several times during the feature extraction of task to achieve task-specific embedding and quickly adapt to different distributed tasks, improves the feature extraction performance, and strikes a balance between model stability and generality. The model employs Euclidean distance as the classifier to reduce the number of model parameters and enhance the classification performance. Experiments conducted on miniImageNet, TieredImageNet, CUB200_2011 and CIFAR-FS datasets demonstrate the performance of the proposed BiLSTM-TANet. Furthermore, the effects of different few-shot learning parameters on the model’s performance are explored, providing a helpful reference for the future study of few-shot learning. Finally, a series of ablation studies are performed to analyze the performance of BiLSTM-TANet.

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

Access this article

Log in via an institution

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

Similar content being viewed by others

Data Availability and Access

The datasets generated or analyzed during this study are available from the corresponding author on reasonable request.

Code Availability

The code is publicly available at https://github.com/Pixelsugar/BiLSTM-TANet.

References

  1. Ma Y, Zhao S, Wang W et al (2022) Multimodality in meta-learning: A comprehensive survey. Knowl-Based Syst 250:108976

  2. Guo R, Liu H, Xie G et al (2021) Weld defect detection from imbalanced radiographic images based on contrast enhancement conditional generative adversarial network and transfer learning. IEEE Sens J 21(9):10844–10853

    Article  Google Scholar 

  3. Li X, Sun Z, Xue JH et al (2021) A concise review of recent few-shot meta-learning methods. Neurocomputing 456:463–468

    Article  Google Scholar 

  4. Yang J, Guo X, Li Y et al (2022) A survey of few-shot learning in smart agriculture: developments, applications, and challenges. Plant Methods 18(1):1–12

    Article  Google Scholar 

  5. Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. Adv Neural Inf Process Syst 30:4077–4087

    Google Scholar 

  6. Liu Y, Zhang H, Zhang W et al (2022) Few-shot image classification: Current status and research trends. Electronics 11(11):1752

    Article  Google Scholar 

  7. Hospedales T, Antoniou A, Micaelli P et al (2021) Meta-learning in neural networks: A survey. IEEE Trans Pattern Anal Mach Intell 44(9):5149–5169

    Google Scholar 

  8. Zhang C, Li C, Cheng J (2019) Few-shot visual classification using image pairs with binary transformation. IEEE Trans Circuits Syst Video Technol 30(9):2867–2871

    Article  Google Scholar 

  9. Ji Z, Hou Z, Liu X et al (2022) Information symmetry matters: a modal-alternating propagation network for few-shot learning. IEEE Trans Image Process 31:1520–1531

    Article  Google Scholar 

  10. Vinyals O, Blundell C, Lillicrap T et al (2016) Matching networks for one shot learning. Adv Neural Inf Process Syst 29:3630–3638

    Google Scholar 

  11. Zhang J, Zhang X, Wang Z (2022) Task encoding with distribution calibration for few-shot learning. IEEE Trans Circuits Syst Video Technol 32(9):6240–6252

    Article  Google Scholar 

  12. Xing L, Shao S, Liu W et al (2022) Learning task-specific discriminative embeddings for few-shot image classification. Neurocomputing 488:1–13

    Article  Google Scholar 

  13. Li Y, Chen CP, Zhang T (2022) A survey on siamese network: Methodologies, applications, and opportunities. IEEE Transactions on artificial intelligence 3(6):994–1014

    Article  Google Scholar 

  14. Huang G, Laradji I, Vazquez D et al (2022) A survey of self-supervised and few-shot object detection. IEEE Trans Pattern Anal Mach Intell 45(4):4071–4089

    Google Scholar 

  15. Ren Z, Zhu Y, Liu Z et al (2023) Few-shot gan: Improving the performance of intelligent fault diagnosis in severe data imbalance. IEEE Transactions on instrumentation and measurement

  16. Goodfellow I, Pouget-Abadie J, Mirza M et al (2020) Generative adversarial networks. Commun ACM 63(11):139–144

    Article  MathSciNet  Google Scholar 

  17. Yang X, Yu Z, Jiang P et al (2022) Deblurring ghost imaging reconstruction based on underwater dataset generated by few-shot learning. Sensors 22(16):6161

    Article  Google Scholar 

  18. Xu B, Zeng Z, Lian C et al (2022) Few-shot domain adaptation via mixup optimal transport. IEEE Trans Image Process 31:2518–2528

    Article  Google Scholar 

  19. Feng R, Ji H, Zhu Z et al (2022) Selfnet: A semi-supervised local fisher discriminant network for few-shot learning. Neurocomputing 512:352–362

    Article  Google Scholar 

  20. Song Y, Wang T, Cai P et al (2023) A comprehensive survey of few-shot learning: Evolution, applications, challenges, and opportunities. ACM Computing Surveys

  21. Wang RQ, Zhang XY, Liu CL (2021) Meta-prototypical learning for domain-agnostic few-shot recognition. IEEE Transactions on neural networks and learning systems 33(11):6990–6996

    Article  Google Scholar 

  22. Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: International conference on machine learning, PMLR, pp 1126–1135

  23. Zhu X, Li S (2022) Mgml: Momentum group meta-learning for few-shot image classification. Neurocomputing 514:351–361

    Article  Google Scholar 

  24. Fu Q, Wang Z, Fang N et al (2023) Maml2: meta reinforcement learning via meta-learning for task categories. Front Comp Sci 17(4):174325

    Article  Google Scholar 

  25. Baik S, Oh J, Hong S et al (2021) Learning to forget for meta-learning via task-and-layer-wise attenuation. IEEE Trans Pattern Anal Mach Intell 44(11):7718–7730

    Article  Google Scholar 

  26. Jiang W, Huang K, Geng J et al (2020) Multi-scale metric learning for few-shot learning. IEEE Trans Circuits Syst Video Technol 31(3):1091–1102

    Article  Google Scholar 

  27. Tian R, Shi H (2023) Momentum memory contrastive learning for transfer-based few-shot classification. Appl Intell 53(1):864–878

    Article  Google Scholar 

  28. Li X, Yang X, Ma Z et al (2023) Deep metric learning for few-shot image classification: A review of recent developments. Pattern Recognition p 109381

  29. Sung F, Yang Y, Zhang L et al (2018) Learning to compare: Relation network for few-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1199–1208

  30. Guo R, Liu H, Xie G et al (2023) A self-interpretable soft sensor based on deep learning and multiple attention mechanism: From data selection to sensor modeling. IEEE Trans Industr Inf 19(5):6859–6871. https://doi.org/10.1109/TII.2022.3181692

    Article  Google Scholar 

  31. Widhianingsih TDA, Kang DK (2022) Augmented domain agreement for adaptable meta-learner on few-shot classification. Appl Intell pp 1–17

  32. Wang Z, Ma P, Chi Z et al (2022) Multi-attention mutual information distributed framework for few-shot learning. Expert Syst Appl 202:117062

    Article  Google Scholar 

  33. Li Z, Hu Z, Luo W et al (2023) Sabernet: Self-attention based effective relation network for few-shot learning. Pattern Recogn 133:109024

    Article  Google Scholar 

  34. Xu W, Xian Y, Wang J et al (2022a) Attribute prototype network for any-shot learning. Int J Comput Vis 130(7):1735–1753

  35. Xu J, Liu B, Xiao Y (2022b) A multitask latent feature augmentation method for few-shot learning. IEEE Transactions on neural networks and learning systems

  36. Cui Z, Lu N, Wang W et al (2022) Dual global-aware propagation for few-shot learning. Image Vis Comput 128:104574

    Article  Google Scholar 

  37. Oreshkin B, Rodríguez López P, Lacoste A (2018) Tadam: Task dependent adaptive metric for improved few-shot learning. Adv Neural Inform Process Syst 31

  38. Requeima J, Gordon J, Bronskill J et al (2019) Fast and flexible multi-task classification using conditional neural adaptive processes. Adv Neural Inform Process Syst 32

  39. Perez E, Strub F, De Vries H et al (2018) Film: Visual reasoning with a general conditioning layer. In: Proceedings of the AAAI conference on artificial intelligence

  40. Bateni P, Goyal R, Masrani V et al (2020) Improved few-shot visual classification. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 14493–14502

  41. Satorras VG, Estrach JB (2018) Few-shot learning with graph neural networks. In: International conference on learning representations

  42. Li L, Jin W, Huang Y (2022) Few-shot contrastive learning for image classification and its application to insulator identification. Appl Intell 52(6):6148–6163

    Article  Google Scholar 

  43. Li W, Wang L, Xu J et al (2019) Revisiting local descriptor based image-to-class measure for few-shot learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 7260–7268

  44. Liu X, Zhou F, Liu J et al (2020) Meta-learning based prototype-relation network for few-shot classification. Neurocomputing 383:224–234

    Article  Google Scholar 

  45. Zhang Y, Wang C, Shi Q et al (2023) Adversarial gradient-based meta learning with metric-based test. Knowl-Based Syst 263:110312

    Article  Google Scholar 

  46. Zhou F, Zhang L, Wei W (2022) Meta-generating deep attentive metric for few-shot classification. IEEE Trans Circuits Syst Video Technol 32(10):6863–6873

  47. Huang H, Wu Z, Li W et al (2021) Local descriptor-based multi-prototype network for few-shot learning. Pattern Recogn 116:107935

    Article  Google Scholar 

  48. Qin Y, Zhang W, Zhao C et al (2021) Prior-knowledge and attention based meta-learning for few-shot learning. Knowl-Based Syst 213:106609

    Article  Google Scholar 

  49. Fu W, Zhou L, Chen J (2022) Bidirectional matching prototypical network for few-shot image classification. IEEE Signal Process Lett 29:982–986

    Article  Google Scholar 

  50. Zhang J, Zhang X, Wang Z (2022) Task encoding with distribution calibration for few-shot learning. IEEE Trans Circuits Syst Video Technol 32(9):6240–6252

    Article  Google Scholar 

  51. Zheng Z, Wu H, Lv L et al (2023) Iccl: Independent and correlative correspondence learning for few-shot image classification. Knowl-Based Syst 266:110412

    Article  Google Scholar 

  52. Bi S, Wang Y, Li X et al (2022) Critical direction projection networks for few-shot learning. Appl Intell 52(5):5400–5413

    Article  Google Scholar 

  53. Yan L, Li F, Zhang L et al (2023) Discriminant space metric network for few-shot image classification. Appl Intell pp 1–16

  54. Asheghi R, Hosseini SA, Saneie M et al (2020) Updating the neural network sediment load models using different sensitivity analysis methods: a regional application. J Hydroinf 22(3):562–577

    Article  Google Scholar 

  55. Abbaszadeh Shahri A, Shan C, Larsson S (2022) A novel approach to uncertainty quantification in groundwater table modeling by automated predictive deep learning. Nat Resour Res 31(3):1351–1373

    Article  Google Scholar 

  56. Abbaszadeh Shahri A, Chunling S, Larsson S (2023) A hybrid ensemble-based automated deep learning approach to generate 3d geo-models and uncertainty analysis. Eng Comput pp 1–16

Download references

Acknowledgements

The authors wish to acknowledge Professor Qing Liu from Xi’an University of Technology for his help in writing the paper.

Funding

This work was supported in part by Major Research Program of National Natural Science Foundation of China under Grants 92270117, Major Instrument Project of National Natural Science Foundation of China under Grants 62127809, The 2023 General Special Scientific Research Program of the Department of Education of Shaanxi Province under Grants 23JK0387, The Doctoral Scientific Research Startup Foundation of Xi’an University of Technology under Grants 103-451123015.

Author information

Author notes

  1. Lili Liang, Wenlu Ma and Ding Liu contributed equally to this work.

Authors and Affiliations

  1. School of Automation and Information Engineering, Xi’an University of Technology, No.5 Jinhua South Road, Xi’an, 710048, Shaanxi, China

    He Zhang, Han Liu, Lili Liang & Ding Liu

  2. School of Information Engineering, Shaanxi Xueqian Normal University, No.101 Shenhe Second Road, Xi’an, 710100, Shaanxi, China

    Wenlu Ma

Authors
  1. He Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Han Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Lili Liang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Wenlu Ma
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Ding Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Experiment, Writing-review editing: He Zhang; Reviewing, Supervision: Han Liu; Reviewing, Proof reading: Lili Liang; Reviewing: Wenlu Ma; Reviewing, Proof reading: Ding Liu.

Corresponding author

Correspondence to Han Liu.

Ethics declarations

Ethical and Informed Consent for Data Used

All authors disclosed no relevant relationships.

Competing Interest

The authors declare that they have no competing interests.

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

Zhang, H., Liu, H., Liang, L. et al. BiLSTM-TANet: an adaptive diverse scenes model with context embeddings for few-shot learning. Appl Intell 54, 5097–5116 (2024). https://doi.org/10.1007/s10489-024-05440-y

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-024-05440-y

Keywords

Search

Navigation