TACDFSL: Task Adaptive Cross Domain Few-Shot Learning

Zhang, Qi; Jiang, Yingluo; Wen, Zhen

doi:10.3390/sym14061097

Cited by 3 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, they also showed that using a larger K can enable a higher classification performance. Other studies (Adler et al., 2020; Cai & Shen, 2020; Jiang et al., 2020) used different meta‐learning methods to conduct a similar experiment, and they achieved results similar to those reported by Guo et al. (2020).…”

Section: Application Of Few‐shot Learning For Model and Optimizationsupporting

confidence: 65%

“…In addition, they also showed that using a larger K can enable a higher classification performance. Other studies (Adler et al, 2020;Cai & Shen, 2020;Jiang et al, 2020) used different meta-learning methods to conduct a similar experiment, and they achieved results similar to those reported by Guo et al (2020). Thus, the performance of meta-learning is expected to improve when the target task is similar to the source tasks and K is large; otherwise, it yields unstable performance.…”

Section: Meta-learningmentioning

confidence: 60%

See 1 more Smart Citation

Few‐shot learning for plant disease recognition: A review

Sun

Cao

et al. 2023

Agronomy Journal

View full text Add to dashboard Cite

Monitoring plant diseases is essential for farmers to secure crop quantity and quality. Deep learning has recently been applied to plant disease recognition to help farmers take prompt and proper actions to prevent reductions in crop quantity and quality. Generally, deep learning requires a large‐scale dataset with supervised information annotated often by specialists. However, because collecting plant disease images in natural environments is difficult and obtaining proper annotations from specialists is costly, deep learning is infeasible for plant disease recognition tasks. Few‐shot learning (FSL) is an alternative for plant disease recognition using prior knowledge. Although FSL has attracted considerable attention, comprehensive reports on the application of FSL methods for plant disease recognition are required. Here, we introduce FSL with its applications in plant disease recognition. We begin with an overview of computer vision tasks using machine learning and FSL. We provide practical examples of FSL applications. Utilizing these practical examples, we describe different approaches for data augmentation and FSL methods of embedding, multitask learning, transfer learning, and meta‐learning. Further, we summarize how models are optimized for performance with reference to existing studies. Finally, the advantages and disadvantages are discussed, along with potential challenges for FSL applications in plant disease recognition.

show abstract

Section: Application Of Few‐shot Learning For Model and Optimizationsupporting

confidence: 65%

Section: Meta-learningmentioning

confidence: 60%

Few‐shot learning for plant disease recognition: A review

Sun

Cao

et al. 2023

Agronomy Journal

View full text Add to dashboard Cite

show abstract

“…the left part of Figure 13 (c). For the former category, in [134], WDMDS (Wasserstein Distance for Measuring Domain Shift) and MMDMDS (Maximum Mean Discrepancy for Measuring Domain Shift) were proposed to solve CDFSL. [118] introduced the MemREIN framework which considers memorization, restitution, and instance normalization, e.g.…”

Section: Feature Transformationmentioning

confidence: 99%

Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey

Xu¹,

Zhi²,

Sun³

et al. 2023

Preprint

View full text Add to dashboard Cite

Deep learning has been highly successful in computer vision with large amounts of labeled data, but struggles with limited labeled training data. To address this, Few-shot learning (FSL) is proposed, but it assumes that all samples (including source and target task data, where target tasks are performed with prior knowledge from source ones) are from the same domain, which is a stringent assumption in the real world. To alleviate this limitation, Cross-domain few-shot learning (CDFSL) has gained attention as it allows source and target data from different domains and label spaces. This paper provides a comprehensive review of CDFSL at the first time, which has received far less attention than FSL due to its unique setup and difficulties. We expect this paper to serve as both a position paper and a tutorial for those doing research in CDFSL. This review first introduces the definition of CDFSL and the issues involved, followed by the core scientific question and challenge. A comprehensive review of validated CDFSL approaches from the existing literature is then presented, along with their detailed descriptions based on a rigorous taxonomy. Furthermore, this paper outlines and discusses several promising directions of CDFSL that deserve further scientific investigation, covering aspects of problem setups, applications and theories.

show abstract