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
Published in:
Experimental and Modeling Study of Open-Hole Composite Laminates Under Tension Read chapter Read first chapter

2023 | OriginalPaper | Chapter

A Survey of Few-Shot Learning for Image Classification of Aerial Objects

Authors : Haoxin Cai, Xuanyue Zhu, Pengcheng Wen, Wei Han, Le Wu

Published in: Proceedings of the 10th Chinese Society of Aeronautics and Astronautics Youth Forum

Publisher: Springer Nature Singapore

Log in

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

search-config
loading …

Abstract

The aircraft has high requirements for effective detection and rapid support in different situations, and in this process, the image classification of aerial objects plays a very important role. In view of the situation that many tasks in the field of image classification of aerial objects cannot get enough samples to learn, it is necessary to study few-shot learning technology, which is mainly divided into three aspects: data based, model based and optimization based. Considering the advantages and disadvantages of various few-shot learning methods and their contribution to the accuracy of few-shot image classification, the developing trend of few-shot learning technology in the field of image classification of aerial objects is summarized. The three research directions of data, model and optimization are not independent of each other, and it is the mainstream to combine them. The application of few-shot learning technology in aviation can realize the deployment of high-precision and high-stability models for aerial tasks with little available data, and reduce the high cost of data tags to a certain extent, which is meaningful. It is hoped that this paper can provide ideas for the application of few-shot learning in the field of aerial image, and then solve practical problems.

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
previous chapter Thermoelastic Analysis in Imperfect Rotating Functionally Graded Disks with Control Volume Finite Element Method
next chapter Remaining Useful Life Prediction Method of Aero-Engines Based on LSTM
Literature
1.
Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(1) (2019)
2.
Wang, Y., Hebert, M.H.: Learning from small sample sets by combining unsupervised meta-training with CNNs. 2016
3.
Boney, R., Ilin, A.: Semi-supervised few-shot learning with MAML (2018)
4.
Ren†, M., Triantafillou∗†, E., Ravi∗§, S., et al.: Meta-learning for semi-supervised few-shot classification[J] (2018)
5.
Liu, Y, Lee, J., Park, M., et al.: Transductive propagation network for few-shot learning[J] (2018)
6.
Hou, R., Chang, H., Ma, B., et al.: Cross attention network for few-shot classification[J] (2019)
7.
Xie, Q., Dai, Z., Hovy, E., et al.: Unsupervised data augmentation for consistency training[J] (2019)
8.
Bateni, P., Barber, J., Goyal, R., et al.: Beyond simple meta-learning: multi-purpose models for multi-domain, active and continual few-shot learning[J]. (2022)
9.
Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al.: Generative Adversarial Nets. MIT Press (2014)
10.
Mehrotra, A., Dukkipati, A.: Generative adversarial residual pairwise networks for one shot learning[J] (2017)
11.
Ali-Gombe, A.: Few-shot classifier GAN. [C]. In: 2018 International Joint Conference on Neural Networks (IJCNN) (2018)
12.
Xian, Y., Sharma, S., Schiele, B., et al.: F-VAEGAN-D2: a feature generating framework for any-shot learning[J]. IEEE (2019)
13.
Nguyen, K., Todorovic, S.: A self-supervised GAN for unsupervised few-shot object recognition[C]. In: 2020 25th International Conference on Pattern Recognition (ICPR) (2021)
14.
LoFGAN: Fusing local representations for few-shot image generation
15.
Pan, H., Yang Xiaogang, L., Ruitao, C.Z., Chuang, L.: Data augmentation method of infrared ship target based on spatial association[J]. Infrared Laser Eng. 50(12), 20210281 (2021)
16.
Liu, B., Zhu, Y., Song, K., et al.: Towards faster and stabilized GAN training for high-fidelity few-shot image synthesis[J]. 2021
17.
Chopra, S., Had Sell R., Lecun, Y.: Learning a similarity metric discriminatively, with application to face verification[C]. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). IEEE (2005)
18.
Wang, J., Zhu, Z., Li, J., et al.: Attention based siamese networks for few-shot learning[C]. In: 2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS). IEEE (2019)
19.
Jadon, S., Srinivasan, A.A.: Siamese networks for one shot learning using kernel-based activation functions[M] (2019)
20.
Shao, H., Zhong, D., Du, X., et al.: Few-shot learning for palmprint recognition via meta-siamese network[J]. IEEE Trans. Instrum. Meas. 70, 1–12 (2021)
21.
Vinyals, O., Blundell, C., Lillicrap, T., et al.: Matching networks for one shot learning[J] (2016)
22.
Mai, S., Hu, H., Xu, J.: Attentive matching network for few-shot learning[J]. Comput. Vis. Image Underst. 187(Oct.), 102781.1–102781.13 (2019)
23.
Li, H., Dong, W., Mei, X., et al.: LGM-Net: learning to generate matching networks for few-shot learning[J] (2019)
24.
Chen, M., Wang, X., Luo, H., et al.: Learning to focus:cascaded feature matching network for few-shot image recognition[J]. Sci. China Inf. Sci. 64(9), 86–98 (2021)CrossRef
25.
Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning[J] (2017)
26.
Fort, S.: Gaussian prototypical networks for few-shot learning on omniglot[J] (2017)
27.
Wang, J., Zhai, Y.: Prototypical siamese networks for few-shot learning[C]. In: 2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC). IEEE (2020)
28.
Lim, J.Y., Lim, K.M., Ooi, S.Y., et al.: Efficient-prototypicalnet with self knowledge distillation for few-shot learning[J]. Neurocomputing 459 (2021)
29.
Sung, F., Yang, Y., Zhang, L., et al.: Learning to compare: relation network for few-shot learning[J] (2017)
30.
Hui, B., Zhu, P., Hu, Q., et al.: Self-attention relation network for few-shot learning[C]. In: 2019 IEEE International Conference on Multimedia & Expo Workshops (ICMEW). IEEE (2019)
31.
Ashrafi, I., Mohammad, M., Mauree, A.S., et al.: Attention guided relation network for few-shot image classification[C]. In: ICCCM (2019)
32.
Abdelaziz, M., Zhang, Z.: Multi-scale kronecker-product relation networks for few-shot learning[J]. Multimed. Tools Appl. 81(5), 6703–6722 (2022)CrossRef
33.
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks[J] (2017)
34.
Li, Z., Zhou, F., Fei, C., et al.: Meta-SGD: learning to learn quickly for few-shot learning[J] (2017)
35.
Jamal, M.A., Qi, G.J., Shah, M.: Task-agnostic meta-learning for few-shot learning[J] (2018)
36.
Xu, H., Wang, J., Li, H., et al.: Unsupervised meta-learning for few-shot learning[J]. Pattern Recogn. 116(6), 107951 (2021)CrossRef
37.
Cao, K., Brbic, M., Leskovec, J.: Concept learners for few-shot learning[J]. ICLR (2021)
38.
Lee, Y., Choi, S.: Gradient-based meta-learning with learned layerwise metric and subspace[J] (2018)
39.
Kim, J., Choi, Y., Cha, M., et al.: Auto-meta: automated gradient based meta learner search[J] (2018)
40.
Dove, H.S., Schwartz, E., Xue, C., et al.: MetAdapt: meta-learned task-adaptive architecture for few-shot classification[J] (2019)
41.
Elsken, T., Staffler, B., Metzen, J.H., et al.: Meta-learning of neural architectures for few-shot learning[C]. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2020)
42.
Larochelle, S.: Optimization as a model for few-shot learning
43.
Antoniou, A., Edwards, H., Storkey, A.: How to train your MAML[J] (2018)
44.
Rusu, A.A., Rao, D., Sygnowski, J., et al.: Meta-learning with latent embedding optimization[J] (2018)
45.
Bertinetto, L., Henriques, J.F., Torr, P., et al.: Meta-learning with differentiable closed-form solvers[J] (2018)
46.
Zhang, B, Li, X, Ye, Y., et al.: MetaNODE: prototype optimization as a neural ODE for few-shot learning[J] (2021)
47.
Tian, P., Gao, Y.: Improving meta-learning model via meta-contrastive loss[J]. Front. Comput. Sci. 16(5), 1–7 (2022)CrossRef
Metadata
Title
A Survey of Few-Shot Learning for Image Classification of Aerial Objects
Authors
Haoxin Cai
Xuanyue Zhu
Pengcheng Wen
Wei Han
Le Wu
Copyright Year
2023
Publisher
Springer Nature Singapore
Book
Proceedings of the 10th Chinese Society of Aeronautics and Astronautics Youth Forum

Print ISBN: 978-981-19-7651-3

Electronic ISBN: 978-981-19-7652-0

Copyright Year: 2023

DOI
https://doi.org/10.1007/978-981-19-7652-0_50

Premium Partner

    Image Credits