2022
DOI: 10.1109/lgrs.2021.3101495
|View full text |Cite
|
Sign up to set email alerts
|

ALPN: Active-Learning-Based Prototypical Network for Few-Shot Hyperspectral Imagery Classification

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
7
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
9

Relationship

0
9

Authors

Journals

citations
Cited by 20 publications
(7 citation statements)
references
References 15 publications
0
7
0
Order By: Relevance
“…To further verify the effectiveness of the proposed AL-MRIS method, several state-of-the-art classification methods, including DRIN [29], 3DCSN [20], S3Net [23], ALPN [26], FAAL [27], CFSL [16] and Gia-CFSL [17], were used for comparison. The corresponding classification maps are shown in Figures 9-12.…”
Section: Comparison Of Different Classification Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…To further verify the effectiveness of the proposed AL-MRIS method, several state-of-the-art classification methods, including DRIN [29], 3DCSN [20], S3Net [23], ALPN [26], FAAL [27], CFSL [16] and Gia-CFSL [17], were used for comparison. The corresponding classification maps are shown in Figures 9-12.…”
Section: Comparison Of Different Classification Methodsmentioning
confidence: 99%
“…Ma et al jointly used iterative training sampling and AL to iteratively update and enhance the initial training sample set to improve the HSI classification accuracy with small training samples [25]. Li et al combined semisupervised clustering technology and the AL strategy to develop an efficient prototype network-based framework that can extract representative features from few-shot samples to enhance representation ability [26]. Wang et al developed an adversarial AL strategy that captures variability HSI features and used advanced features to obtain heuristics through adversarial learning [27].…”
Section: Introductionmentioning
confidence: 99%
“…Active Learning (AL) has been considered an effective method to reduce the labeling cost as well as acquire a large number of labeled training samples [66]. AL is based on three main aspects; 1): The availability of initial training set X train , 2): The availability of pool set (validation set in this work) X val , 3): Query function e.g., informative sample selection or acquisition function.…”
Section: B Active Learning (Al)mentioning
confidence: 99%
“…Apart from pre-processing, existing works also focus on addressing FS classification issues through the design of training strategies, which can be roughly categorized as strict Few-Shot Learning (FSL) [10,11], semi-supervised learning (SSL) [12,13], and active learning (AL) [14,15]. FSL models often rely on meta-learning training strategies that utilize a limited number of labeled samples and an auxiliary set to construct multiple meta-learning tasks [16], enabling the acquisition of an initialization model with strong generalization capabilities.…”
Section: Introductionmentioning
confidence: 99%