An attention-based prototypical network for forest fire smoke few-shot detection

Existing almost deep learning methods rely on a large amount of annotated data, so they are inappropriate for forest fire smoke detection with limited data. In this paper, a novel hybrid attention-based few-shot learning method, named Attention-Based Prototypical Network, is proposed for forest fire...

Full description

Saved in:
Bibliographic Details
Published in:Journal of forestry research 2022-10, Vol.33 (5), p.1493-1504
Main Authors: Li, Tingting, Zhu, Haowei, Hu, Chunhe, Zhang, Junguo
Format: Article
Language:English
Subjects:
Biomedical and Life Sciences
Computational linguistics
Datasets
Deep learning
False alarms
Feature extraction
Forest fires
Forestry
Forests
Language processing
Life Sciences
Machine learning
Modules
Natural language interfaces
Original Paper
Smoke
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Existing almost deep learning methods rely on a large amount of annotated data, so they are inappropriate for forest fire smoke detection with limited data. In this paper, a novel hybrid attention-based few-shot learning method, named Attention-Based Prototypical Network, is proposed for forest fire smoke detection. Specifically, feature extraction network, which consists of convolutional block attention module, could extract high-level and discriminative features and further decrease the false alarm rate resulting from suspected smoke areas. Moreover, we design a meta-learning module to alleviate the overfitting issue caused by limited smoke images, and the meta-learning network enables achieving effective detection via comparing the distance between the class prototype of support images and the features of query images. A series of experiments on forest fire smoke datasets and miniImageNet dataset testify that the proposed method is superior to state-of-the-art few-shot learning approaches.
ISSN:1007-662X
1993-0607
DOI:10.1007/s11676-022-01457-6