Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.3
2.5
Journals
Applied Sciences
Special Issues
Recent Advances in Few-Shot Learning for Computer Vision Tasks
applsci-logo
Submit to Applied Sciences Review for Applied Sciences Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Recent Advances in Few-Shot Learning for Computer Vision Tasks

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (31 December 2023) | Viewed by 4402

Special Issue Editor

Prof. Dr. Fan Liu

E-Mail Website
Guest Editor
Department of Computer Science and Technology, College of Computer and Information, Hohai University, Nanjing 210098, China
Interests: computer vision; pattern recognition; deep learning
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Deep learning has brought revolutionary advancements in the area of computer vision. However, the data-hungry property of deep neural networks has greatly limited their practical application. Few-shot learning (FSL) is a type of machine learning problem, where experience contains only a limited number of examples with supervised information for the target. As a way of learning like humans, FSL has attracted a lot of attention in various computer vision tasks. Recently, many classical few-shot learning models have been put forward successively, bringing in significant development in this field of research. However, there is currently still a gap compared with human intelligence, even for the best FSL model. Determining how to further improve the performance of FSL models and accelerate their prompt application in practical scenarios is definitely a topic worth studying.

The topic of this Special Issue covers a wide range of algorithms, methods, and applications of few-shot learning. Topics of interest include but are not limited to:

  • Theory of few-shot learning;
  • Conventional few-shot learning;
  • Data augmentation for few-shot learning;
  • Cross-domain few-shot learning;
  • Cross-modal few-shot learning;
  • Few-shot classification;
  • Few-shot object detection;
  • Few-shot semantic segmentation;
  • Few-shot learning with pre-trained models.

Dr. Fan Liu
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • few-shot learning
  • computer vision
  • deep learning

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (2 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

15 pages, 1540 KiB  
Article
Few-Shot Image Classification via Mutual Distillation
by Tianshu Zhang, Wenwen Dai, Zhiyu Chen, Sai Yang, Fan Liu and Hao Zheng
Appl. Sci. 2023, 13(24), 13284; https://doi.org/10.3390/app132413284 - 15 Dec 2023
Cited by 1 | Viewed by 1629
Abstract
Due to their compelling performance and appealing simplicity, metric-based meta-learning approaches are gaining increasing attention for addressing the challenges of few-shot image classification. However, many similar methods employ intricate network architectures, which can potentially lead to overfitting when trained with limited samples. To [...] Read more.
Due to their compelling performance and appealing simplicity, metric-based meta-learning approaches are gaining increasing attention for addressing the challenges of few-shot image classification. However, many similar methods employ intricate network architectures, which can potentially lead to overfitting when trained with limited samples. To tackle this concern, we propose using mutual distillation to enhance metric-based meta-learning, effectively bolstering model generalization. Specifically, our approach involves two individual metric-based networks, such as prototypical networks and relational networks, mutually supplying each other with a regularization term. This method seamlessly integrates with any metric-based meta-learning approach. We undertake comprehensive experiments on two prevalent few-shot classification benchmarks, namely miniImageNet and Caltech-UCSD Birds-200-2011 (CUB), to demonstrate the effectiveness of our proposed algorithm. The results demonstrate that our method efficiently enhances each metric-based model through mutual distillation. Full article
(This article belongs to the Special Issue Recent Advances in Few-Shot Learning for Computer Vision Tasks)
►▼ Show Figures

Figure 1

13 pages, 3079 KiB  
Article
Global and Local Knowledge Distillation Method for Few-Shot Classification of Electrical Equipment
by Bojun Zhou, Jiahao Zhao, Chunkai Yan, Xinsong Zhang and Juping Gu
Appl. Sci. 2023, 13(12), 7016; https://doi.org/10.3390/app13127016 - 10 Jun 2023
Cited by 3 | Viewed by 1680
Abstract
With the increasing utilization of intelligent mobile devices for online inspection of electrical equipment in smart grids, the limited computing power and storage capacity of these devices pose challenges for deploying large algorithm models, and it is also difficult to obtain a substantial [...] Read more.
With the increasing utilization of intelligent mobile devices for online inspection of electrical equipment in smart grids, the limited computing power and storage capacity of these devices pose challenges for deploying large algorithm models, and it is also difficult to obtain a substantial number of images of electrical equipment in public. In this paper, we propose a novel distillation method that compresses the knowledge of teacher networks into a compact few-shot classification network, employing a global and local knowledge distillation strategy. Central to our method is exploiting the global and local relationships between the features exacted by the backbone of the teacher network and the student network. We compared our method with recent state-of-the-art (SOTA) methods on three public datasets, and we achieved superior performance. Additionally, we contribute a new dataset, namely, EEI-100, which is specifically designed for electrical equipment image classification. We validated our method on this dataset and demonstrated its exceptional prediction accuracy of 94.12% when utilizing only 5-shot images. Full article
(This article belongs to the Special Issue Recent Advances in Few-Shot Learning for Computer Vision Tasks)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-2
Back to TopTop