skip to main content
10.1145/3652583.3658114acmconferencesArticle/Chapter ViewAbstractPublication PagesicmrConference Proceedingsconference-collections
research-article

A Hybrid Few-Shot Image Classification Framework Combining Gaussian Modeling and Label Propagation

Published: 07 June 2024 Publication History

Abstract

Humans possess the remarkable ability to recognize new objects with merely a handful of labeled examples, whereas contemporary deep learning models continue to face challenges in few-shot learning scenarios, primarily due to the scarcity of training data. In this study, we concentrate on addressing the challenges associated with transductive and semi-supervised few-shot image classification, both methods permitting the incorporation of unlabeled data during the training phase. To fully leverage the potential of unlabeled data, we explore a variety of unsupervised and semi-supervised learning approaches, including manifold learning, aimed at uncovering the intrinsic properties of the data. Specifically, we employ the locality preserving projection method as a powerful enabling technique for discriminative feature learning. The features learned are integrated into our proposed hybrid few-shot learning (FSL) framework, collaboratively augmenting the performance of few-shot image classification. Our proposed hybrid FSL framework capitalizes on the synergistic capabilities of both the parametric Gaussian model and the non-parametric label propagation model through a straightforward score-level ensemble learning approach. Consequently, our methodology yields superior outcomes on four benchmark datasets (miniImageNet, tieredImageNet, CUB, and CIFAR-FS), for both transductive and semi-supervised few-shot image classification tasks.

References

[1]
Luca Bertinetto, Joao F Henriques, Philip HS Torr, and Andrea Vedaldi. 2018. Meta-learning with differentiable closed-form solvers. arXiv preprint arXiv:1805.08136 (2018).
[2]
Xiangyu Chen and Guanghui Wang. 2021. Few-shot learning by integrating spatial and frequency representation. In 2021 18th Conference on Robots and Vision (CRV). IEEE, 49--56.
[3]
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770--778.
[4]
Xiaofei He and Partha Niyogi. 2003. Locality preserving projections. Advances in neural information processing systems, Vol. 16 (2003).
[5]
Yuqing Hu, Vincent Gripon, and Stéphane Pateux. 2020. Exploiting unsupervised inputs for accurate few-shot classification. arXiv preprint arXiv:2001.09849, Vol. 2 (2020).
[6]
Yuqing Hu, Vincent Gripon, and Stéphane Pateux. 2021. Leveraging the feature distribution in transfer-based few-shot learning. In Artificial Neural Networks and Machine Learning--ICANN 2021: 30th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 14--17, 2021, Proceedings, Part II 30. Springer, 487--499.
[7]
Yuqing Hu, Stéphane Pateux, and Vincent Gripon. 2023. Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification. In International Conference on Artificial Intelligence and Statistics. PMLR, 5899--5917.
[8]
Jongyoo Kim and Sanghoon Lee. 2017. Deep learning of human visual sensitivity in image quality assessment framework. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1676--1684.
[9]
Philip A Knight. 2008. The Sinkhorn--Knopp algorithm: convergence and applications. SIAM J. Matrix Anal. Appl., Vol. 30, 1 (2008), 261--275.
[10]
Seong Min Kye, Hae Beom Lee, Hoirin Kim, and Sung Ju Hwang. 2020. Meta-learned confidence for few-shot learning. arXiv preprint arXiv:2002.12017 (2020).
[11]
Michalis Lazarou, Tania Stathaki, and Yannis Avrithis. 2021. Iterative label cleaning for transductive and semi-supervised few-shot learning. In Proceedings of the ieee/cvf international conference on computer vision. 8751--8760.
[12]
Xinzhe Li, Qianru Sun, Yaoyao Liu, Qin Zhou, Shibao Zheng, Tat-Seng Chua, and Bernt Schiele. 2019. Learning to self-train for semi-supervised few-shot classification. Advances in neural information processing systems, Vol. 32 (2019).
[13]
Moshe Lichtenstein, Prasanna Sattigeri, Rogerio Feris, Raja Giryes, and Leonid Karlinsky. 2020. Tafssl: Task-adaptive feature sub-space learning for few-shot classification. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part VII. Springer, 522--539.
[14]
Yanbin Liu, Juho Lee, Minseop Park, Saehoon Kim, Eunho Yang, Sung Ju Hwang, and Yi Yang. 2018. Learning to propagate labels: Transductive propagation network for few-shot learning. arXiv preprint arXiv:1805.10002 (2018).
[15]
Xiaohuan Lu, Jiang Long, Jie Wen, Lunke Fei, Bob Zhang, and Yong Xu. 2022. Locality preserving projection with symmetric graph embedding for unsupervised dimensionality reduction. Pattern Recognition, Vol. 131 (2022), 108844.
[16]
Puneet Mangla, Nupur Kumari, Abhishek Sinha, Mayank Singh, Balaji Krishnamurthy, and Vineeth N Balasubramanian. 2020. Charting the right manifold: Manifold mixup for few-shot learning. In Proceedings of the IEEE/CVF winter conference on applications of computer vision. 2218--2227.
[17]
Mengye Ren, Eleni Triantafillou, Sachin Ravi, Jake Snell, Kevin Swersky, Joshua B Tenenbaum, Hugo Larochelle, and Richard S Zemel. 2018. Meta-learning for semi-supervised few-shot classification. arXiv preprint arXiv:1803.00676 (2018).
[18]
Pau Rodr'iguez, Issam Laradji, Alexandre Drouin, and Alexandre Lacoste. 2020. Embedding propagation: Smoother manifold for few-shot classification. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XXVI 16. Springer, 121--138.
[19]
Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, et al. 2015. Imagenet large scale visual recognition challenge. International journal of computer vision, Vol. 115 (2015), 211--252.
[20]
Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical networks for few-shot learning. Advances in neural information processing systems, Vol. 30 (2017).
[21]
Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip HS Torr, and Timothy M Hospedales. 2018. Learning to compare: Relation network for few-shot learning. Proceedings of the IEEE conference on computer vision and pattern recognition (2018), 1199--1208.
[22]
Olivier Veilleux, Malik Boudiaf, Pablo Piantanida, and Ismail Ben Ayed. 2021. Realistic evaluation of transductive few-shot learning. Advances in Neural Information Processing Systems, Vol. 34 (2021), 9290--9302.
[23]
Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Daan Wierstra, et al. 2016. Matching networks for one shot learning. Advances in neural information processing systems, Vol. 29 (2016).
[24]
Catherine Wah, Steve Branson, Peter Welinder, Pietro Perona, and Serge Belongie. 2011. The caltech-ucsd birds-200--2011 dataset. California Institute of Technology (2011).
[25]
Qian Wang and Toby Breckon. 2020. Unsupervised domain adaptation via structured prediction based selective pseudo-labeling. In Proceedings of the AAAI conference on artificial intelligence, Vol. 34. 6243--6250.
[26]
Qian Wang and Toby P Breckon. 2022. Cross-domain structure preserving projection for heterogeneous domain adaptation. Pattern Recognition, Vol. 123 (2022), 108362.
[27]
Yikai Wang, Chengming Xu, Chen Liu, Li Zhang, and Yanwei Fu. 2020. Instance credibility inference for few-shot learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 12836--12845.
[28]
Kai Xu, Minghai Qin, Fei Sun, Yuhao Wang, Yen-Kuang Chen, and Fengbo Ren. 2020. Learning in the frequency domain. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 1740--1749.
[29]
Sergey Zagoruyko and Nikos Komodakis. 2016. Wide residual networks. arXiv preprint arXiv:1605.07146 (2016).
[30]
Hao Zhu and Piotr Koniusz. 2022. EASE: Unsupervised discriminant subspace learning for transductive few-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 9078--9088.
[31]
Hao Zhu and Piotr Koniusz. 2023. Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinement. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 23996--24006.

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
ICMR '24: Proceedings of the 2024 International Conference on Multimedia Retrieval
May 2024
1379 pages
ISBN:9798400706196
DOI:10.1145/3652583
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 07 June 2024

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. discriminant subspace learning
  2. few-shot learning
  3. label propagation

Qualifiers

  • Research-article

Funding Sources

  • The National Key Research and Development Program of China

Conference

ICMR '24
Sponsor:

Acceptance Rates

Overall Acceptance Rate 254 of 830 submissions, 31%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 57
    Total Downloads
  • Downloads (Last 12 months)57
  • Downloads (Last 6 weeks)11
Reflects downloads up to 14 Feb 2025

Other Metrics

Citations

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media