Skip to main content

Advertisement

Springer Nature Link
Log in

Few-shot contrastive learning for image classification and its application to insulator identification

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

This paper presents a novel discriminative Few-shot learning architecture based on batch compact loss. Currently, Convolutional Neural Network (CNN) has achieved reasonably good performance in image recognition. Most existing CNN methods facilitate classifiers to learn discriminating patterns to identify existing categories trained with large samples. However, learning to recognize novel categories from a few examples is a challenging task. To address this, we propose the Residual Compact Network to train a deep neural network to learn hierarchical nonlinear transformations to project image pairs into the same latent feature space, under which the distance of each positive pair is reduced. To better use the commonality of class-level features for category recognition, we develop a batch compact loss to form robust feature representations relevant to a category. The proposed methods are evaluated on several datasets. Experimental evaluations show that our proposed method achieves acceptable results in Few-shot learning.

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
Fig. 5
Fig. 6

Similar content being viewed by others

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

References

  1. Anselme N, TN H, Hyeon KD, Tae KK, Seon HC (2021) Deep learning based caching for Self-Driving cars in Multi-Access edge computing. IEEE Trans Intell Transp Syst 22(5):2862–2877. https://doi.org/10.1109/tits.2020.2976572

    Article  Google Scholar 

  2. Justin K, Lipo W, Jai R, Tchoyoson L (2018) Deep learning applications in medical image analysis. IEEE Access 6:9375–9389. https://doi.org/10.1109/access.2017.2788044

    Article  Google Scholar 

  3. Alberto G -G, Sergio O -E, Sergiu O, Victor V -M, Pablo M -G, Jose G -R (2018) A survey on deep learning techniques for image and video semantic segmentation. Appl Soft Comput 70:41–65. https://doi.org/10.1016/j.asoc.2018.05.018

    Article  Google Scholar 

  4. Yan Q, Guangning W, Zhang X, Yujun G, Xueqin Z, Kai L (2019) An Extreme-Learning-Machine-Based hyperspectral detection method of insulator pollution degree. IEEE Access 7:121156–121164. https://doi.org/10.1109/access.2019.2937885

    Article  Google Scholar 

  5. Zhenbing Z, Xiaoqing F, Guozhi X, Lei Z, Yincheng Q, Ke Z (2017) Aggregating deep convolutional feature maps for insulator detection in infrared images. IEEE Access 5:21831–21839. https://doi.org/10.1109/access.2017.2757030

    Article  Google Scholar 

  6. Damira M, Aidana I, JP K, Mehdi B (2020) Multi-Modal Data fusion using deep neural network for condition monitoring of high voltage insulator. IEEE Access 8:184486–184496. https://doi.org/10.1109/access.2020.3027825

    Article  Google Scholar 

  7. Hao J, Xiaojie Q, Jing C, Xinyu L, Xiren M, Shengbin Z (2019) Insulator fault detection in aerial images based on ensemble learning with Multi-Level perception. IEEE Access 7:61797–61810. https://doi.org/10.1109/access.2019.2915985

    Article  Google Scholar 

  8. Wenqiang L, Zhigang L, Hui W, Zhiwei H (2020) An automated defect detection approach for catenary Rod-Insulator textured surfaces using unsupervised learning. IEEE Trans Instrum Meas 69 (10):8411–8423. https://doi.org/10.1109/tim.2020.2987503

    Google Scholar 

  9. Shixin H, Xiangping Z, Si W, Zhiwen Y, Mohamed A, Hau-San W (2021) Behavior regularized prototypical networks for semi-supervised few-shot image classification. Pattern Recogn 112:107765–107775. https://doi.org/10.1016/j.patcog.2020.107765

    Article  Google Scholar 

  10. Jin-Woo S, Hong-Gyu J, Seong-Whan L (2021) Self-augmentation: Generalizing deep networks to unseen classes for few-shot learning. Neural Netw 138:140–149. https://doi.org/10.1016/j.neunet.2021.02.007

    Article  Google Scholar 

  11. Jingyao W, Zhibin Z, Chuang S, Ruqiang Y, Xuefeng C (2020) Few-shot transfer learning for intelligent fault diagnosis of machine. Measurement 166:108202–108214. https://doi.org/10.1016/j.measurement.2020.108202

    Article  Google Scholar 

  12. Chongyu P, Jian H, Jianxing G, Xingsheng Y (2019) Few-Shot Transfer learning for text classification with lightweight word embedding based models. IEEE Access 7:53296–53304. https://doi.org/10.1109/access.2019.2911850

    Article  Google Scholar 

  13. Oriol V, Charles B, Timothy L, Koray K, Daan W (2016) Matching networks for one shot learning. In: Advances in Neural Information Processing Systems, vol 29. Curran Associates, Barcelona, pp 3630–3638

  14. Zhong J, Xingliang C, Yunlong Y, Yanwei P, Zhongfei Z (2020) Improved prototypical networks for few-Shot learning. Pattern Recogn Lett 140:81–87. https://doi.org/10.1016/j.patrec.2020.07.015

    Article  Google Scholar 

  15. Flood S, Yongxin Y, Li Z, Tao X, Philip HST, Timothy MH Learning to Compare: Relation Network for Few-Shot Learning. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, Salt Lake City, pp 1199–1208. https://doi.org/10.1109/CVPR.2018.00131

  16. Jake S, Kevin S, Richard SZ Prototypical Networks for Few-shot Learning. In: 31st International Conference on Neural Information Processing Systems. Curran Associates Inc, Long Beach, pp 4080–4090. https://doi.org/10.5555/3294996.3295163

  17. KC-C A, Thanos T, KV T, Giorgos S, GI F (2020) Hydrophobicity classification of composite insulators based on convolutional neural networks. Eng Appl Artif Intell 91:103613–103622. https://doi.org/10.1016/j.engappai.2020.103613

    Article  Google Scholar 

  18. Yanqing L, Lichun S, Qin H, Xingliang J, Meilin Z, Zhou Y, Hanxiang L (2021) Statistical analysis on the DC discharge path of ice-covered insulators under natural conditions. Int J Electr Power Energy Syst 130:106961–106967. https://doi.org/10.1016/j.ijepes.2021.106961

  19. Sampedro C, Rodriguez-Vazquez J, Rodriguez-Ramos A, Carrio A, Campoy P (2019) Deep Learning-Based system for automatic recognition and diagnosis of electrical insulator strings. IEEE Access 7:101283–101308. https://doi.org/10.1109/access.2019.2931144

    Article  Google Scholar 

  20. Xian T, Dapeng Z, Zihao W, Xilong L, Hongyan Z, De X (2020) Detection of power line insulator defects using aerial images analyzed with convolutional neural networks. IEEE Trans Syst Man Cybern-Syst 50(4):1486–1498. https://doi.org/10.1109/tsmc.2018.2871750

    Article  Google Scholar 

  21. Diana S, Damira P, Mehdi B, Alex J (2020) IN-YOLO: Real-Time detection of outdoor high voltage insulators using UAV imaging. IEEE Trans Power Deliv 35(3):1599–1601. https://doi.org/10.1109/tpwrd.2019.2944741

    Article  Google Scholar 

  22. Ansi Z, Shaobo L, Yuxin C, Wanli Y, Rongzhi D, Jianjun H (2019) Limited data rolling bearing fault diagnosis with Few-Shot learning. IEEE Access 7:110895–110904. https://doi.org/10.1109/access.2019.2934233

    Article  Google Scholar 

  23. Sonal D, VN K, GA K (2021) Intelligent fault diagnosis of rotary machines: Conditional auxiliary classifier GAN coupled with meta learning using limited data. IEEE Trans Instrum Meas 70:1–11. https://doi.org/10.1109/tim.2021.3082264

    Google Scholar 

  24. Toshitaka H, Hamido F, Andres H -M (2021) Less complexity one-class classification approach using construction error of convolutional image transformation network. Inf Sci 560:217–234. https://doi.org/10.1016/j.ins.2021.01.069

    Article  MathSciNet  Google Scholar 

  25. Toshitaka H, Hamido F (2020) Cluster-based zero-shot learning for multivariate data. J Ambient Intell Human Comput 12(2):1897–1911. https://doi.org/10.1007/s12652-020-02268-5

    Google Scholar 

  26. Zhaohong D, Yizhang J, Hisao I, Kup-Sze C, Shitong W (2016) Enhanced Knowledge-Leverage-Based TSK fuzzy system modeling for inductive transfer learning. ACM Trans Intell Syst Technol 8(1):1–21. https://doi.org/10.1145/2903725

    Google Scholar 

  27. Siwei F, DM F (2019) Few-shot learning-based human activity recognition. Expert Syst Appl 138:112782–112793. https://doi.org/10.1016/j.eswa.2019.06.070

    Article  Google Scholar 

  28. Wenhe L, Xiaojun C, Yan Y, Yi Y, HA G (2018) Few-Shot Text and image classification via analogical transfer learning. ACM Trans Intell Syst Technol 9(6):1–20. https://doi.org/10.1145/3230709

    Google Scholar 

  29. David A, Artzai P, Unai I, Alfonso M, s-EM, G, Arantza B, Aitor A-G (2020) Few-Shot Learning approach for plant disease classification using images taken in the field. Comput Electron Agric 175:105542–105549. https://doi.org/10.1016/j.compag.2020.105542

    Article  Google Scholar 

  30. Lixiao X, Zhaohong D, Peng X, Kup-Sze C, Shitong W (2019) Generalized Hidden-Mapping transductive transfer learning for recognition of epileptic electroencephalogram signals. IEEE Trans Cybern 49 (6):2200–2214. https://doi.org/10.1109/TCYB.2018.2821764

    Article  Google Scholar 

  31. Sachin R, Hugo L (2017) Optimization as a Model for Few-Shot Learning. In: 5th International Conference on Learning Representations, Toulon. OpenReview.net

  32. Chelsea F, Pieter A, Sergey L Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. In: Proceedings of the 34th International Conference on Machine Learning. PMLR, Sydney, pp 1126–1135

  33. RA A, Dushyant R, Jakub S, Oriol V, Razvan P, Simon O, Raia H (2019) Meta-learning with Latent Embedding Optimization. In: 7th International Conference on Learning Representations. OpenReview.net, New Orleans

  34. Junbo L, Yaping H, Mei ZQT (2019) Learning visual similarity for inspecting defective railway fasteners. IEEE Sens J 19(16):6844–6857. https://doi.org/10.1109/jsen.2019.2911015

    Article  Google Scholar 

  35. Shafin R, Salman K, Fatih P (2018) A Unified approach for Conventional Zero-shot, Generalized Zero-shot and Few-shot Learning. IEEE Trans Image Process 27(11):5652–5667. https://doi.org/10.1109/TIP.2018.2861573

    Article  MathSciNet  Google Scholar 

  36. Mohammad S, Hossain MS (2021) MetaCOVID: A Siamese neural network framework with contrastive loss for n-shot diagnosis of COVID-19 patients. Pattern Recogn 113:107700–107710. https://doi.org/10.1016/j.patcog.2020.107700

    Article  Google Scholar 

  37. Xiaocong C, Lina Y, Tao Z, Jinming D, Yu Z (2021) Momentum contrastive learning for few-shot COVID-19 diagnosis from chest CT images. Pattern Recogn 113:107826–107833. https://doi.org/10.1016/j.patcog.2021.107826

    Article  Google Scholar 

  38. Ran W, Yaoyi L, Haiyan L, Ze T, Hongtao L, Nengbin C, Xuejun Z (2021) A robust and effective text detector supervised by Contrastive Learning. IEEE Access:26431–26441. https://doi.org/10.1109/access.2021.3057108

  39. Haifeng Z, Wen S, Zengfu W (2020) Weakly supervised Local-Global attention network for facial expression recognition. IEEE Access 8:37976–37987. https://doi.org/10.1109/access.2020.2975913

    Article  Google Scholar 

  40. Junling G, Lei X, Ayache B, Mingxi W (2019) A deep Siamese-Based plantar fasciitis classification method using shear wave elastography. IEEE Access 7:130999–131007. https://doi.org/10.1109/access.2019.2940645

    Article  Google Scholar 

  41. Siyuan Y, Hua Z, Wenqi R, Chao M, Xiaoguang H, Xiaochun C (2021) Robust online tracking via contrastive Spatio-Temporal aware network. IEEE Trans Image Process 30:1989–2002. https://doi.org/10.1109/TIP.2021.3050314

    Article  Google Scholar 

  42. Bac N, Carlos M, Bernard DB (2018) Distance metric learning for ordinal classification based on triplet constraints. Knowl-Based Syst 142:17–28. https://doi.org/10.1016/j.knosys.2017.11.022

    Article  Google Scholar 

  43. Jianqing Z, Huanqiang Z, Shengcai L, Zhen L, Canhui C, Lixin Z (2018) Deep hybrid similarity learning for person Re-Identification. IEEE Trans Circ Syst Video Technol 28(11):3183–3193. https://doi.org/10.1109/tcsvt.2017.2734740

    Article  Google Scholar 

  44. Xiaoyan Z, Yu W, Yingbini L, Yonghui T, Guangtao W, Qinbao S (2019) A new unsupervised feature selection algorithm using similarity-based feature clustering. Comput Intell 35:2–22. https://doi.org/10.1111/coin.12192

    Article  MathSciNet  Google Scholar 

  45. Gong C, Ceyuan Y, Xiwen Y, Lei G, Junwei H (2018) When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNs. IEEE Trans Geosci Remote Sens 56(5):2811–2821. https://doi.org/10.1109/tgrs.2017.2783902

    Article  Google Scholar 

  46. Chuan-Xian R, Xiao-Lin X, Zhen L (2019) A deep and structured metric learning method for robust person Re-Identification. Pattern Recogn 96:106995–107006. https://doi.org/10.1016/j.patcog.2019.106995

    Article  Google Scholar 

  47. Ha KD, Cheol SB (2021) Virtual sample-based deep metric learning using discriminant analysis. Pattern Recogn 110:107643–107656. https://doi.org/10.1016/j.patcog.2020.107643

    Article  Google Scholar 

  48. Xi Y, Haoyuan G, Nannan W, Bin S, Xinbo G (2020) A Novel Symmetry Driven Siamese Network for THz Concealed Object Verification. IEEE Trans Image Process 29:5447–5456. https://doi.org/10.1109/TIP.2020.2983554

    Article  Google Scholar 

  49. Yibang R, Yanshan X, Zhifeng H, Bo L (2021) A nearest-neighbor search model for distance metric learning. Inf Sci 552:261–277. https://doi.org/10.1016/j.ins.2020.11.054

    Article  MathSciNet  Google Scholar 

  50. Min C, Yongxin G, Xin F, Chuanyun X, Dan Y (2018) Person Re-Identification by pose invariant deep metric learning with improved triplet loss. IEEE Access 6:68089–68095. https://doi.org/10.1109/access.2018.2879490

    Article  Google Scholar 

  51. Hantao Y, Shiliang Z, Richang H, Yongdong Z, Changsheng X, Qi T (2019) Deep Representation Learning with Part Loss for Person Re-Identification. IEEE Trans Image Process 28(6):2860–2871. https://doi.org/10.1109/TIP.2019.2891888

    Article  MathSciNet  MATH  Google Scholar 

  52. Kaiming H, Xiangyu Z, Shaoqing R, Jian S Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, Las Vegas, pp 770–778. https://doi.org/10.1109/CVPR.2016.90

  53. Andreas V, Michael W, Serge B (2016) Residual networks behave like ensembles of relatively shallow networks. In: Advances in Neural Information Processing Systems, vol 29. Curran Associates, Barcelona, pp 550–558

  54. Weiyang L, Yandong W, Zhiding Y, Ming L, Bhiksha R, Le S SphereFace: Deep Hypersphere Embedding for Face Recognition. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, Honolulu, pp 6738–6746. https://doi.org/10.1109/CVPR.2017.713

  55. Prannay K, Piotr T, Chen W, Aaron S, Yonglong T, Phillip I, Aaron M, Ce L, Dilip K Supervised Contrastive Learning. In: Advances in Neural Information Processing Systems, vol 33. Annual Conference on Neural Information Processing Systems 2020, virtual. Curran Associates

  56. Bac N, Bernard DB (2020) Improved deep embedding learning based on stochastic symmetric triplet loss and local sampling. Neurocomputing 402:209–219. https://doi.org/10.1016/j.neucom.2020.04.062

    Article  Google Scholar 

  57. Kihyuk S (2016) Improved Deep Metric Learning with Multi-class N-pair Loss Objective, vol 29. Curran Associates, Barcelona

    Google Scholar 

  58. David M, Camilo N, Carlos C, Martha M, Francisco H (2020) Incremental learning model inspired in Rehearsal for deep convolutional networks. Knowl-Based Syst 208:106460–106480. https://doi.org/10.1016/j.knosys.2020.106460

    Article  Google Scholar 

  59. Lake BM, Salakhutdinov R, Gross J, Tenenbaum JB One shot learning of simple visual concepts. In: Proceedings of the 33th Annual Meeting of the Cognitive Science Society. cognitivesciencesociety.org, Boston, pp 2568–2573

  60. Mengye R, Eleni T, Sachin R, Jake S, Kevin S, Joshua BT, Hugo L, Richard SZ (2018) Meta-learning for Semi-Supervised Few-Shot Classification. In: 6th International Conference on Learning Representations. OpenReview.net, Vancouver

  61. Qizhe X, Zihang D, HE H, Thang L, Quoc L (2020) Unsupervised Data Augmentation for Consistency Training. In: Advances in Neural Information Processing Systems, vol 33. Annual Conference on Neural Information Processing Systems, virtual. Curran Associate

  62. Adam S, Sergey B, Matthew B, Daan W (2016) Timothy PL Meta-Learning with Memory-Augmented Neural Networks. In: Proceedings of the 33nd International Conference on Machine Learning. JMLR.org, New York, pp 1842– 1850

  63. James R, Jonathan G, John B, Sebastian N (2019) Richard ET fast and flexible Multi-Task classification using conditional neural adaptive processes. In: Advances in Neural Information Processing Systems, vol 32. PMLR, Vancouver, pp 7957– 7968

  64. Łukasz K, Ofir N, Aurko R, Samy B (2017) Learning to Remember Rare Events. In: 5th International Conference on Learning Representations. OpenReview.net, Toulon

  65. Harrison E (2017) Neural Statistician. In: 5th International Conference on Learning Representations, Palais des Congrés NeptuneOpenReview.net, Toulon

  66. Tsendsuren M, Hong Y (2017) Meta Networks. In: Proceedings of the 34th International Conference on Machine Learning. PMLR, Sydney, pp 2554–2563

  67. WR F (2008) Wilcoxon Signed-Rank test. Wiley encyclopedia of clinical trials, pp 1–3. https://doi.org/10.1002/9780471462422.eoct979

  68. Wenbin L, Jinglin X, Jing H, Lei W, Yang G, Jiebo L (2019) Distribution Consistency Based Covariance Metric Networks for Few-Shot Learning. In: The Thirty-Third AAAI Conference on Artificial Intelligence. AAAI, Palo Alto, pp 8642–8649. https://doi.org/10.1609/aaai.v33i01.33018642

Download references

Author information

Authors and Affiliations

  1. Southwest Jiaotong University, Chengdu City, Sichuan Province, China

    Liang Li, Weidong Jin & Yingkun Huang

  2. China-ASEAN International Joint Laboratory of Integrated Transportation, Nanning University, Nanning City, Guangxi Province, China

    Weidong Jin

Authors
  1. Liang Li
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Weidong Jin
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Yingkun Huang
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Liang Li.

Additional information

Publisher’s note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, L., Jin, W. & Huang, Y. Few-shot contrastive learning for image classification and its application to insulator identification. Appl Intell 52, 6148–6163 (2022). https://doi.org/10.1007/s10489-021-02769-6

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-021-02769-6

Keywords