Exploring Meta Learning: Parameterizing the Learning-to-learn Process for Image Classification

So, Chaehan

doi:10.1109/icaiic51459.2021.9415205

Cited by 5 publications

(2 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meta-learning is an emerging research framework within the realm of machine learning [20]. The primary objective of meta-learning is to endow models with the capability to acquire learning abilities, which allow them to automatically assimilate meta-knowledge, encompasses information that can be learned outside the standard model training process, such as model hyperparameters, the initial parameters of the neural network, network architectures, and optimization strategies, among other elements [21].…”

Section: Deep Learning and Meta-learningmentioning

confidence: 99%

Fault Diagnosis Based on Tensor Computing and Meta-Learning for Smart Grid and Power Communication Network

Yu,

Guan,

Tian

et al. 2024

Electronics

View full text Add to dashboard Cite

Fault diagnosis (FD) is a critical challenge for the smart grid and the power communication network, especially when both heterogeneous networks are exponentially becoming enormous and complicated. Consequently, some conventional FD schemes based on labor seem inefficient, even disabled, because they usually cannot efficiently utilize multi-dimensional and heterogeneous big data from both networks. To deal with this challenging technical problem, a novel FD scheme based on tensor computing and meta-learning is proposed for the smart grid and the power communication network. In the proposed scheme, tensor computing is used to process tensor big data from both networks, and a new data fusion scheme is designed to complete and analyze the incomplete and sparse big data. Based on the fused data, a meta-learning approach is used to construct the FD scheme, especially when the target fault samples are inadequate and sparse. In meta-learning, the convolutional neural network is employed as a base learner to generate an FD training model, and the model-agnostic meta-learning algorithm is utilized to fine-tune and further train the pre-trained model. Simulation results and theoretical analysis indicate that the proposed DF scheme based on tensor computing can efficiently process sparse and heterogeneous big data from both networks. Furthermore, the meta-learning-based FD scheme provides an efficient way to diagnose faults with inadequate target samples. The proposed FD scheme based on tensor computing and meta-learning provides a novel solution to detect and analyze the potential faults for smart grid and power communication networks.

show abstract

Section: Deep Learning and Meta-learningmentioning

confidence: 99%

Fault Diagnosis Based on Tensor Computing and Meta-Learning for Smart Grid and Power Communication Network

Yu,

Guan,

Tian

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…In the overall MAFSL framework, this paper performs few-shot learning on mini-ImageNet to learn transferable prior knowledge. In the meta-learning [14] strategy, the dataset is divided into support and query sets. First, 𝐶 classes are selected from the mini-ImageNet dataset, and then 𝐾 labeled samples are selected from each of the selected classes as the support set, which is represented as…”

Section: Few-shot Learning On Mini-imagenetmentioning

confidence: 99%

Multi-scale attention-based few-shot hyperspectral images classification

Ding

Cao

et al. 2023

Fourteenth International Conference on Graphics and Image Processing (ICGIP 2022)

View full text Add to dashboard Cite

In recent years, deep learning-based hyperspectral image classification techniques have developed rapidly. Many effective deep learning models have been proposed in academia, such as 3D-CNN and some other CNN-based methods, which have achieved high accuracy in hyperspectral image classification. These excellent methods rely on large number of labeled samples for their effectiveness. In practice, labeling pixels of hyperspectral images is expensive (time-consuming and labor-intensive), so it is often difficult to obtain enough labeled samples for training deep neural network models. To address this problem, we propose a multiscale attention-based few-shot learning (MAFSL) method using only a few labeled samples for each category in this paper. First, few-shot learning is performed on mini-ImageNet to obtain prior knowledge, and then the knowledge is transferred to the hyperspectral dataset. Before embedding features, multiscale attention-based feature extraction with reconstruction loss is applied to the hyperspectral image. Then, the obtained features are input into the spatial feature extraction network and the spectral extraction network, respectively. Finally, the embedded features are put into the metric space for classification. The proposed model can get a higher classification accuracy because the extracted features have less correlation with each other. Experimental results show that our MAFSL outperforms many existing supervised learning methods when only a small number of labeled samples are used.

show abstract

MAML-Based D2D Power Control Scheme in User-Variable Scenario

Fan¹,

Xu²

2023

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

Exploring Meta Learning: Parameterizing the Learning-to-learn Process for Image Classification

Cited by 5 publications

References 1 publication

Fault Diagnosis Based on Tensor Computing and Meta-Learning for Smart Grid and Power Communication Network

Fault Diagnosis Based on Tensor Computing and Meta-Learning for Smart Grid and Power Communication Network

Multi-scale attention-based few-shot hyperspectral images classification

MAML-Based D2D Power Control Scheme in User-Variable Scenario

Contact Info

Product

Resources

About