Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
Springer Nature Link
Log in

Few-shot classification with intra-class co-salient learning and holistic metric

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Few-shot learning is to learn to discriminate novel classes from a minimal amount of support images. The core of the matter lies in obtaining effective feature representations from limited samples and measuring the similarity between query and support images. In this paper, we approach this problem from two perspectives: effective feature learning and similarity measurement. We observe that the objects being classified are typically the common salient targets within the support class in few-shot classification. Based on this observation, we design a Co-Salient Feature Extraction module which can learn the correlations among the intra-class samples in the support images, thereby making the learned features more representative of the class. Regarding similarity measurement, we comprehensively consider both the global features and local details of the images and propose a Multi-Scale Metric module to implement holistic metric and improve the reliability of image-to-class measurement. We conduct experiments on four benchmark datasets for few-shot image classification, including general object recognition, fine-grained categorization, and cross-domain classification. The experimental results in various few-shot learning scenarios demonstrate that the proposed Intra-class Co-Salient (ICoS) network achieves competitive performance, particularly excelling in fine-grained classification, ICoS outperforms the similarity techniques DN4 by 20.61% in 1-shot and 11.23% in 5-shot on the CUB dataset, demonstrating the validity of co-salient 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
Fig. 7

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data availability

Datasets generated during the current study are available from the corresponding author on reasonable request.

References

  1. Wang Y, Yao Q, Kwok JT, Ni LM (2020) Generalizing from a few examples: a survey on few-shot learning. ACM Comput Surv (csur) 53(3):1–34

    Article  Google Scholar 

  2. Lu J, Gong P, Ye J, Zhang C (2020) Learning from very few samples: a survey, arXiv preprint arXiv:2009.02653

  3. Ren L, Duan G, Huang T, Kang Z (2022) Multi-local feature relation network for few-shot learning. Neural Comput Appl 34(10):7393–7403

    Article  Google Scholar 

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

  5. Wu Z, Shen C, Guo K, Luo E, Wang L (2023) Nc 2 e: boosting few-shot learning with novel class center estimation. Neural Comput Appl 35(9):7049–7062

    Article  Google Scholar 

  6. Chen Y, Liu Z, Xu H, Darrell T, Wang X (2021) Meta-baseline: exploring simple meta-learning for few-shot learning. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 9062–9071

  7. Mangla P, Kumari N, Sinha A, Singh M, Krishnamurthy B, Balasubramanian VN (2020) Charting the right manifold: manifold mixup for few-shot learning. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision, pp 2218–2227

  8. Tian Y, Wang Y, Krishnan D, Tenenbaum JB, Isola P (2020) Rethinking few-shot image classification: a good embedding is all you need?. In: Computer vision–ECCV 2020: 16th European conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XIV 16, Springer, pp 266–282

  9. Chen W-Y, Liu Y-C, Kira Z, Wang Y-C F, Huang J-B (2019) A closer look at few-shot classification, arXiv preprint arXiv:1904.04232

  10. Nichol A, Achiam J, Schulman J (2018) On first-order meta-learning algorithms, arXiv preprint arXiv:1803.02999

  11. Xue W, Wang W (2020) One-shot image classification by learning to restore prototypes. In: Proceedings of the AAAI conference on artificial intelligence, Vol 34, pp 6558–6565

  12. Liu J, Song L, Qin Y (2020) Prototype rectification for few-shot learning. In: Computer vision–ECCV 2020: 16th European conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part I 16, Springer, pp 741–756

  13. Vinyals O, Blundell C, Lillicrap T, Wierstra D, et al (2016) Matching networks for one shot learning. Adv Neural Inf Process Syst 29

  14. Li W, Wang L, Xu J, Huo J, Gao Y, Luo J (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

  15. Cheng M-M, Mitra NJ, Huang X, Torr PH, Hu S-M (2014) Global contrast based salient region detection. IEEE Trans Pattern Anal Mach Intell 37(3):569–582

    Article  Google Scholar 

  16. 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

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

    Article  Google Scholar 

  18. Rao S, Huang J, Tang Z (2023) Adaptive regularized warped gradient descent enhances model generalization and meta-learning for few-shot learning. Neurocomputing 537:271–281

    Article  Google Scholar 

  19. Li A, Huang W, Lan X, Feng J, Li Z, Wang L (2020) Boosting few-shot learning with adaptive margin loss. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 12576–12584

  20. Liu B, Cao Y, Lin Y, Li Q, Zhang Z, Long M, Hu H (2020) Negative margin matters: understanding margin in few-shot classification. In: Computer vision–ECCV 2020: 16th European conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part IV 16, Springer, pp 438–455

  21. Li X, Li Y, Zheng Y, Zhu R, Ma Z, Xue J-H, Cao J (2023) Renap: relation network with adaptiveprototypical learning for few-shot classification. Neurocomputing 520:356–364

    Article  Google Scholar 

  22. Li G, Jampani V, Sevilla-Lara L, Sun D, Kim J, Kim J (2021) Adaptive prototype learning and allocation for few-shot segmentation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 8334–8343

  23. Gao T, Han X, Liu Z, Sun M (2019) Hybrid attention-based prototypical networks for noisy few-shot relation classification. In: Proceedings of the AAAI conference on artificial intelligence, Vol 33, pp 6407–6414

  24. Chikontwe P, Kim S, Park SH (2022) Cad: co-adapting discriminative features for improved few-shot classification. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 14554–14563

  25. Ji Z, Chai X, Yu Y, Zhang Z (2021) Reweighting and information-guidance networks for few-shot learning. Neurocomputing 423:13–23

    Article  Google Scholar 

  26. Sung F, Yang Y, Zhang L, Xiang T, Torr PH, Hospedales TM (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

  27. Li X, Yu L, Fu C-W, Fang M, Heng P-A (2020) Revisiting metric learning for few-shot image classification. Neurocomputing 406:49–58

    Article  Google Scholar 

  28. Zhang C, Cai Y, Lin G, Shen C (2020) Deepemd: Few-shot image classification with differentiable earth mover’s distance and structured classifiers. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 12203–12213

  29. Xie J, Long F, Lv J, Wang Q, Li P (2022) Joint distribution matters: deep brownian distance covariance for few-shot classification. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 7972–7981

  30. Ge W, Yu Y (2017) Borrowing treasures from the wealthy: deep transfer learning through selective joint fine-tuning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1086–1095

  31. Tian R, Shi H (2023) A transfer-based few-shot classification approach via masked manifold mixup and fuzzy memory contrastive learning. Neural Comput Appl 35(14):10069–10082

    Article  Google Scholar 

  32. Zhou L, Cui P, Jia X, Yang S, Tian Q (2020) Learning to select base classes for few-shot classification. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 4624–4633

  33. Dhillon GS, Chaudhari P, Ravichandran A, Soatto S (2019) A baseline for few-shot image classification, arXiv preprint arXiv:1909.02729

  34. Khosla A, Jayadevaprakash N, Yao B, Li F-F (2011) Novel dataset for fine-grained image categorization: stanford dogs. In: Proceedings CVPR workshop on fine-grained visual categorization (FGVC), Vol. 2, Citeseer

  35. Krause J, Stark M, Deng J, Fei-Fei L (2013) 3d object representations for fine-grained categorization. In: Proceedings of the IEEE international conference on computer vision workshops, pp 554–561

  36. Wah C, Branson S, Welinder P, Perona P, Belongie S (2011) The caltech-ucsd birds-200-2011 dataset

  37. Lee K, Maji S, Ravichandran A, Soatto S (2019) Meta-learning with differentiable convex optimization. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 10657–10665

  38. Garcia V, Bruna J (2017) Few-shot learning with graph neural networks, arXiv preprint arXiv:1711.04043

  39. Snell J, Zemel R (2020) Bayesian few-shot classification with one-vs-each pólya-gamma augmented gaussian processes, arXiv preprint arXiv:2007.10417

  40. Oh J, Yoo H, Kim C, Yun S-Y (2020) Boil: towards representation change for few-shot learning. arXiv preprint arXiv:2008.08882

  41. Ke T, Cao H, Ling Z, Zhou F (2023) Revisiting logistic-softmax likelihood in bayesian meta-learning for few-shot classification. arXiv preprint arXiv:2310.10379

  42. Liu Y, Zhang W, Xiang C, Zheng T, Cai D, He X (2022) Learning to affiliate: mutual centralized learning for few-shot classification. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 14411–14420

  43. Snell J, Zemel R (2020) Bayesian few-shot classification with one-vs-each pólya-gamma augmented gaussian processes. In: International conference on learning representations

  44. Wang X, Girshick R, Gupta A, He K (2018) Non-local neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7794–7803

Download references

Acknowledgements

This work was supported by the Natural Science Foundation of Hunan Province, China, under Grants 2022JJ30746.

Author information

Authors and Affiliations

  1. School of Automation, Central South University, No.932 South Lushan Road, Changsha, 410083, Hunan, China

    Baifan Chen, Ruyi Zhu, Lingli Yu & Yuqian Zhao

Authors
  1. Baifan Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ruyi Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Lingli Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yuqian Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ruyi Zhu.

Ethics declarations

Conflict of interest

The authors have no relevant financial or non-financial interests to disclose.

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

Chen, B., Zhu, R., Yu, L. et al. Few-shot classification with intra-class co-salient learning and holistic metric. Neural Comput & Applic 36, 14327–14339 (2024). https://doi.org/10.1007/s00521-024-09866-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-024-09866-w

Keywords

Search

Navigation