Hierarchy-guided Neural Networks for Species Classification [article]

Mohannad Elhamod, Kelly M. Diamond, A. Murat Maga, Yasin Bakis, Henry L. Bart, Paula Mabee, Wasila Dahdul, Jeremy Leipzig, Jane Greenberg, Brian Avants, Anuj Karpatne
2021 bioRxiv   pre-print
AbstractFish species classification is an important task that is the foundation of many industrial, commercial, ecological, and scientific applications involving the study of fish 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
more » ... ic classes.In this work, we propose infusing phylogenetic information into the model's training to guide its structure and relationships among the extracted features. In our extensive experimental analyses, the proposed model, named Hierarchy-Guided Neural Network (HGNN), outperforms conventional ConvNet models in terms of classification accuracy 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.
doi:10.1101/2021.01.17.427006 fatcat:gywge4n62jbqjpm4jlc3seyjey