What Identifies A Whale by Its Fluke? On the Benefit of Interpretable Machine Learning for Whale Identification

6Citations
Citations of this article
12Readers
Mendeley users who have this article in their library.

Abstract

Interpretable and explainable machine learning have proven to be promising approaches to verify the quality of a data-driven model in general as well as to obtain more information about the quality of certain observations in practise. In this paper, we use these approaches for an application in the marine sciences to support the monitoring of whales. Whale population monitoring is an important element of whale conservation, where the identification of whales plays an important role in this process, for example to trace the migration of whales over time and space. Classical approaches use photographs and a manual mapping with special focus on the shape of the whale flukes and their unique pigmentation. However, this is not feasible for comprehensive monitoring. Machine learning methods, especially deep neural networks, have shown that they can efficiently solve the automatic observation of a large number of whales. Despite their success for many different tasks such as identification, further potentials such as interpretability and their benefits have not yet been exploited. Our main contribution is an analysis of interpretation tools, especially occlusion sensitivity maps, and the question of how the gained insights can help a whale researcher. For our analysis, we use images of humpback whale flukes provided by the Kaggle Challenge "Humpback Whale Identification". By means of spectral cluster analysis of heatmaps, which indicate which parts of the image are important for a decision, we can show that the they can be grouped in a meaningful way. Moreover, it appears that characteristics automatically determined by a neural network correspond to those that are considered important by a whale expert.

References Powered by Scopus

Deep residual learning for image recognition

174329Citations
N/AReaders
Get full text

Focal Loss for Dense Object Detection

17412Citations
N/AReaders
Get full text

Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization

15236Citations
N/AReaders
Get full text

Cited by Powered by Scopus

Explain it to me-facing remote sensing challenges in the bio-and geosciences with explainable machine learning

28Citations
N/AReaders
Get full text

Humpback whale abundance in Hawai‘i: Temporal trends and response to climatic drivers

19Citations
N/AReaders
Get full text

AQ-Bench A benchmark dataset for machine learning on global air quality metrics

19Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Kierdorf, J., Garcke, J., Behley, J., Cheeseman, T., & Roscher, R. (2020). What Identifies A Whale by Its Fluke? On the Benefit of Interpretable Machine Learning for Whale Identification. In ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences (Vol. 5, pp. 1005–1012). Copernicus GmbH. https://doi.org/10.5194/isprs-annals-V-2-2020-1005-2020

Readers over time

‘20‘21‘22‘23‘2402468

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 6

75%

Professor / Associate Prof. 2

25%

Readers' Discipline

Tooltip

Computer Science 3

43%

Agricultural and Biological Sciences 2

29%

Engineering 1

14%

Medicine and Dentistry 1

14%

Save time finding and organizing research with Mendeley

Sign up for free
0