Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top
International Journal of Machine Learning and Cybernetics
Published in: International Journal of Machine Learning and Cybernetics 5/2023

12-12-2022 | Original Article

Few-shot learning based on enhanced pseudo-labels and graded pseudo-labeled data selection

Authors: Kang Wang, Xuesong Wang, Yuhu Cheng

Published in: International Journal of Machine Learning and Cybernetics | Issue 5/2023

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Pseudo-labeled data is used to solve the data shortage in few-shot learning, in which the quality of pseudo-labels and pseudo-labeled data selection determine the classification performance. In order to obtain the enhanced pseudo-labels, we used diverse inputs to encourage the label network to learn invariant and robust representations, improving the generalization ability. Simultaneously, the depthwise over-parameterized convolutional layer and group residual connection with shared parameters accelerate the network training and overcome the time-consuming caused by diverse inputs. Then, the graded pseudo-labeled data selection is proposed to determine various quantities of pseudo-labeled data based on the label network’s performance level, which improves the classification accuracy and avoids the high consumption caused by using all the pseudo-labeled data. Finally, we solved the data shortage in food recognition with the proposed method. The experiments show that our method has better classification accuracy and generalization ability in few-shot benchmark datasets and food recognition with few samples.
previous article Interaction-based clustering algorithm for feature selection: a multivariate filter approach
next article Maximal consistent block based optimal scale selection for incomplete multi-scale information systems

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

inform now
Show more products
Literature
1.
Gao F, Cai L, Yang Z, Song S, Wu C (2022) Multi-distance metric network for few-shot learning. Int J Mach Learn Cybern 13(9):2495–2506CrossRef
2.
Wang K, Wang X, Zhang T, Cheng Y (2022) Few-shot learning with deep balanced network and acceleration strategy. Int J Mach Learn Cybern 13(1):133–144CrossRef
3.
Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of the International Conference on Machine Learning (ICML), Sydney, AUSTRALIA, pp 1126–1135
4.
5.
6.
Santoro A, Bartunov S, Botvinick M, Wierstra D, Lillicrap T (2016) Meta-learning with memory-augmented neural netowrks. In: Proceedings of the International Conference on Machine Learning (ICML), New York City, NY, USA, pp 1842–1850
7.
Munkhdalai T, Yuan X, Mehri, S et al (2018) Rapid adaptation with conditionally shifted neurons. In: Proceedings of the International Conference on Machine Learning (ICML), Stockholm, SWEDEN, pp 3661–3670
8.
9.
Li S, Chen D, Liu B, et al (2019) Memory-based neighbourhood embedding for visual recognition. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), Seoul, Koera (South), pp 6101–6110
10.
Vinyals O, Blundell C, Lillicrap T, et al (2016) Matching networks for one shot learning. In: Proceedings of the Advances in Neural Information Processing Systems (NIPS), Barcelona, SPAIN, pp 3630–3638
11.
Snell J, Swersky K, Zemel RS (2017) Prototypical networks for few-shot learning. In: Proceedings of the Advances in Neural Information Processing Systems (NIPS), Long Beach, CA, USA, pp 4077–4087
12.
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 (CVPR), Salt Lake City, UT, USA, pp 1199–1208
13.
Oreshkin BN, Rodriguez P, Lacoste A (2018) Tadam: task dependent adaptive metric for improved few-shot learning. In: Proceedings of the Advances in Neural Information Processing Systems (NIPS), Montréal , CANADA, pp 719–729
14.
Antoniou A, Storkey A, Edwards H (2017) Data augmentation generative adversarial networks. arXiv: 1711.04340
15.
Zhang R, Che T, Ghahramani Z et al (2018) Metagan: an adversarial approach to few-shot learning. In: Proceedings of the Advances in Neural Information Processing Systems (NIPS), Montréal, CANADA, pp 2371–2380
16.
17.
Xu W, Li W (2016) Granular computing approach to two-way learning based on formal concept analysis in fuzzy datasets. IEEE Trans Cybern 46(2):366–379MathSciNetCrossRef
18.
Li K, Zhang Y, Li K, Fu, Y (2020) Adversarial feature hallucination networks for few-shot learning. arXiv: 2003.13193
19.
Kim J, Kim H, Kim G (2020) Model-agnostic boundary-adversarial sampling for test-time generalization in few-shot learning. In: Proceedings of the European Conference on Computer Vision (ECCV), ELECTR NETWORK, pp 599–6175
20.
Chen Z, Fu Y, Wang Y, Ma L, Liu W, Hebert M (2019) Image deformation meta-networks for one-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp 8672–8681
21.
Zhang H, Zhang J, Koniusz P (2019) Few-shot learning via saliency-guided hallucination of samples. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp 2765–2774
22.
Wang Y, Xu C, Liu C, Zhang L, Fu Y (2020) Instance credibility inference for few-shot learning. arXiv: 2003.11853
23.
Lee K, Lee K, Shin J, Lee H (2019) Network randomization: a simple technique for generalization in deep reinforcement learning. arXiv: 1910.05396v3
24.
Cao J, Li Y, Sun M, et al (2020) DO-Conv: depthwise over-parameterized convolutional layer. arXiv: 2006.12030
25.
Wang X, Yu S (2020) Tied block convolution: leaner and better CNNs with shared thinner filters. arXiv: 2009.12021
26.
Bertinetto L, Henriques J, Torr P, Vedaldi A (2018) Meta-learning with differentiable closed-form solvers. arXiv: 1805.08136
27.
Ren M, Triantafillou E, Ravi S, Snell J, Swersky K, Tenenbaum J, Larochelle H, Zemel R (2018) Meta-learning for semi-supervised few-shot classification. arXiv: 1803.00676
28.
Liu Y, Lee J, Park M, Kim S, Yang E, Hwang S, Yang L (2018) Learning to propagate labels: transductive propagation network for few-shot learning. arXiv: 1805.10002
29.
Simon C, Koniusz P, Nock R, Harandi M (2020) Adaptive subspaces for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), ELECTR NETWORK, pp 4135–4144
30.
Lee H, Hwang S, Shin J (2019) Self-supervised label augmentation via input transformations. arXiv: 1910.05872
31.
Khrulkov V, Mirvakhabova L, Ustinova E, Oseledets I, Lempitsky V. (2019) Hyperbolic image embeddings. arXiv: 1904.02239
32.
Luo Q, Wang L, Lv J, Xiang S, Pan C (2021) Few-shot learning via feature hallucination with variational inference. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), ELECTR NETWORK, pp 3962–3971
33.
Majumder O, Ravichandran A, Maji S, Polito M, Soatto S (2021) Revisiting contrastive learning for few-shot classification. arXiv: 2101.11058
34.
Chen W, Liu Y, Kira Z, Wang Y, Huang J (2019) A closer look at few-shot classification. arXiv: 1904.04232
35.
Zhang Y, Huang S, Peng X, Yang D (2021) Dizygotic conditional variational autoencoder for multi-modal and partial modality absent few-shot learning. arXiv: 2106.14467
36.
Kang D, Kwon H, Min J, Cho M (2021) Relational embedding for few-shot classification. arXiv: 2108.09666
37.
Afrasiyabi A, Lalonde JF, Gagné C (2020) Mixture-based feature space learning for few-shot image classification. arXiv: 2011.11872
38.
Ye H, Ming L, Zhan D, Chao W (2021) Few-shot learning with a strong teacher. arXiv: 2107.00197
39.
Yuan M, Wang W, Wang T, Cai C, Xu Q, Lu, T (2021) Learning class-level prototypes for few-shot learning. arXiv: 2108.11072
40.
Dhillon G, Chaudhari P, Ravichandran A, Soatto S (2019) A baseline for few-shot image classification. arXiv: 1909.02729
41.
Lee E, Huang C, Lee C. (2021) Few-shot and continual learning with attentive independent mechanisms. arXiv: 2107.14053
42.
Schwarcz S, Rambhatla S, Chellappa R (2021) Self-denoising neural networks for few shot learning. arXiv: 2110.13386
43.
Li W, Wang L, Huo J, Shi Y, Gao Y, Luo J (2020) Asymmetric distribution measure for few-shot learning. arXiv: 2002.00153
44.
Yu Z, Raschka S (2020) Looking back to lower-level information in few-shot learning. arXiv: 2005.13638
45.
Lee K, Maij S, Ravichandran A, Soatto S (2019) Meta-learning with differentiable convex optimization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp 10649–10657
46.
Ren M, Liao R, Fetaya E, Zemel R. (2018) Incremental few-shot learning with attention attractor networks. arXiv: 1810.07218
47.
Qiao L, Shi Y, Li J, Tian Y, Huang T, Wang Y (2019) Transductive episodic-wise adaptive metric for few-shot learning. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), Seoul, Korea (South), pp 3602–3611
48.
Ravichandran A, Bhotika R, Soatto S (2019) Few-shot learning with embedded class models and shot-free meta training. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), Seoul, Korea (South), pp 331–339
49.
Tian Y, Wang Y, Krishnan D, Tenenbau J, Isola P (2020) Rethinking few-shot image classification: a good embedding is all you need? In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), ELECTR NETWORK, pp 266–282
50.
51.
Lazarou M, Avrithis Y, Stathaki T (2021) Few-shot learning via tensor hallucination. arXiv: 2104.09467
52.
Sun Q, Liu Y, Chen Z, Tat-Seng C, Bernt S (2022) Meta-transfer learning through hard tasks. IEEE Trans Pattern Anal Mach Intell 44(3):1443–1456CrossRef
53.
Lifchitz Y, Avrithis Y, Picard S, Bursuc A (2019) Dense classification and implanting for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp 9250–9259
54.
Afrasiyabi A, Lalonde JF, Gagne C (2020) Associative alignment for few-shot image classification. In: Proceedings of the European Conference on Computer Vision (ECCV), ELECTR NETWORK, pp 18–35
55.
Wah C, Branson S, Welinder P, Perona P, Belongie S (2011) “The caltech-ucsd birds-200–2011 dataset. Computation& Neural Systems Technical Report. CNS-TR-2011–001
56.
Hilliard N, Phillips L, Howland S, Yankov A, Corley C, Hodas N (2018) Few-shot learning with metric-agnostic conditional embeddings. arXiv: 1802.04376
57.
Patacchiola M, Turner J, Crowley E, O’Boyle M, Storkey A (2019) Bayesian meta-learning for the few-shot setting via deep kernels. arXiv: 1910.05199
58.
Lazarou M, Avrithis Y, Stathaki T (2021) Tensor feature hallucination for few-shot learning. arXiv: 2106.05321
59.
Bossard L, Guillaumin M, Gool L (2014) Food-101–mining discriminative components withrandom forests,” In: Proceedings of the European Conference on Computer Vision (ECCV), Zurich, SWITZERLAND, pp 446–461
60.
Chen X, Zhu Y, Zhou H, Diao L, Wang D (2017) ChineseFoodNet: a large-scale image dataset for chinese food recognition. arXiv: 1705.02743
61.
Jiang S, Min W, Lv Y, Liu L (2020) Few-shot food recognition via multi-view representation learning. ACM Trans Multimed Comput Commun Appl 16(3):1–20CrossRef
Metadata
Title
Few-shot learning based on enhanced pseudo-labels and graded pseudo-labeled data selection
Authors
Kang Wang
Xuesong Wang
Yuhu Cheng
Publication date
12-12-2022
Publisher
Springer Berlin Heidelberg
Published in
International Journal of Machine Learning and Cybernetics / Issue 5/2023
Print ISSN: 1868-8071
Electronic ISSN: 1868-808X
DOI
https://doi.org/10.1007/s13042-022-01727-z

Other articles of this Issue 5/2023

International Journal of Machine Learning and Cybernetics 5/2023 Go to the issue

Original Article

Multi-label sequence generating model via label semantic attention mechanism

Original Article

Generative face inpainting hashing for occluded face retrieval

Original Article

A novel consensus model with probabilistic linguistic preference relation for the utilization mode selection of renewable energy sources

Original Article

Heterogeneous dual network with feature consistency for domain adaptation person re-identification

Original Article

Fusing collaborative transformation with temporally aware target interaction networks for sequential recommendation

Original Article

TAGNet: a tiny answer-guided network for conversational question generation