期刊
METHODS IN ECOLOGY AND EVOLUTION
卷 13, 期 3, 页码 642-652出版社
WILEY
DOI: 10.1111/2041-210X.13768
关键词
machine learning; neural networks; science guided machine learning; species classification; taxonomy
类别
资金
- National Science Foundation through Harnessing the Data Revolution Ideas Lab program awards [1940322, 1940233, 2022042, 1940247, 1939505]
- XSEDE [TG-DEB200005]
- Direct For Computer & Info Scie & Enginr
- Office of Advanced Cyberinfrastructure (OAC) [2022042, 1940233, 1940247] Funding Source: National Science Foundation
- Office of Advanced Cyberinfrastructure (OAC)
- Direct For Computer & Info Scie & Enginr [1939505, 1940322] Funding Source: National Science Foundation
Species classification is a crucial task laying the groundwork for various applications involving species studies. The proposed hierarchy-guided neural network (HGNN) method outperforms traditional ConvNet models in terms of classification accuracy and robustness, especially in scenarios with limited training data.
Species classification is an important task which is the foundation of industrial, commercial, ecological and scientific applications involving the study of species distributions, dynamics and evolution. While conventional approaches for this task use off-the-shelf machine learning (ML) methods such as existing Convolutional Neural Network (ConvNet) architectures, there is an opportunity to inform the ConvNet architecture using our knowledge of biological hierarchies among taxonomic classes. In this work, we propose a new approach for species classification termed hierarchy-guided neural network (HGNN), which infuses hierarchical taxonomic information into the neural network's training to guide the structure and relationships among the extracted features. We perform extensive experiments on an illustrative use-case of classifying fish species to demonstrate that HGNN outperforms conventional ConvNet models in terms of classification accuracy, especially under scarce training data conditions. We also observe that HGNN shows better resilience to adversarial occlusions, when some of the most informative patch regions of the image are intentionally blocked and their effect on classification accuracy is studied.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据