A Whale’s Tail - Finding the Right Whale in an Uncertain World
Explainable machine learning and uncertainty quantification have emerged as promising approaches to check the suitability and understand the decision process of a data-driven model, to learn new insights from data, but also to get more information about the quality of a specific observation. In part...
Main Authors: | , , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Springer
2022
|
Subjects: | |
Online Access: | https://research.wur.nl/en/publications/a-whales-tail-finding-theright-whale-inanuncertain-world https://doi.org/10.1007/978-3-031-04083-2_15 |
id |
ftunivwagenin:oai:library.wur.nl:wurpubs/597525 |
---|---|
record_format |
openpolar |
spelling |
ftunivwagenin:oai:library.wur.nl:wurpubs/597525 2024-04-28T08:23:22+00:00 A Whale’s Tail - Finding the Right Whale in an Uncertain World Marcos, Diego Kierdorf, Jana Cheeseman, Ted Tuia, Devis Roscher, Ribana 2022 application/pdf https://research.wur.nl/en/publications/a-whales-tail-finding-theright-whale-inanuncertain-world https://doi.org/10.1007/978-3-031-04083-2_15 en eng Springer https://edepot.wur.nl/570250 https://research.wur.nl/en/publications/a-whales-tail-finding-theright-whale-inanuncertain-world doi:10.1007/978-3-031-04083-2_15 https://creativecommons.org/licenses/by/4.0/ Wageningen University & Research xxAI - Beyond Explainable AI - International Workshop, Held in Conjunction with ICML 2020, Revised and Extended Papers ISBN: 9783031040825 Attention maps Sensitivity Uncertainty Whale identification Article in monograph or in proceedings 2022 ftunivwagenin https://doi.org/10.1007/978-3-031-04083-2_15 2024-04-03T14:51:38Z Explainable machine learning and uncertainty quantification have emerged as promising approaches to check the suitability and understand the decision process of a data-driven model, to learn new insights from data, but also to get more information about the quality of a specific observation. In particular, heatmapping techniques that indicate the sensitivity of image regions are routinely used in image analysis and interpretation. In this paper, we consider a landmark-based approach to generate heatmaps that help derive sensitivity and uncertainty information for an application in marine science to support the monitoring of whales. Single whale identification is important to monitor the migration of whales, to avoid double counting of individuals and to reach more accurate population estimates. Here, we specifically explore the use of fluke landmarks learned as attention maps for local feature extraction and without other supervision than the whale IDs. These individual fluke landmarks are then used jointly to predict the whale ID. With this model, we use several techniques to estimate the sensitivity and uncertainty as a function of the consensus level and stability of localisation among the landmarks. For our experiments, we use images of humpback whale flukes provided by the Kaggle Challenge “Humpback Whale Identification” and compare our results to those of a whale expert. Article in Journal/Newspaper Humpback Whale Wageningen UR (University & Research Centre): Digital Library 297 313 |
institution |
Open Polar |
collection |
Wageningen UR (University & Research Centre): Digital Library |
op_collection_id |
ftunivwagenin |
language |
English |
topic |
Attention maps Sensitivity Uncertainty Whale identification |
spellingShingle |
Attention maps Sensitivity Uncertainty Whale identification Marcos, Diego Kierdorf, Jana Cheeseman, Ted Tuia, Devis Roscher, Ribana A Whale’s Tail - Finding the Right Whale in an Uncertain World |
topic_facet |
Attention maps Sensitivity Uncertainty Whale identification |
description |
Explainable machine learning and uncertainty quantification have emerged as promising approaches to check the suitability and understand the decision process of a data-driven model, to learn new insights from data, but also to get more information about the quality of a specific observation. In particular, heatmapping techniques that indicate the sensitivity of image regions are routinely used in image analysis and interpretation. In this paper, we consider a landmark-based approach to generate heatmaps that help derive sensitivity and uncertainty information for an application in marine science to support the monitoring of whales. Single whale identification is important to monitor the migration of whales, to avoid double counting of individuals and to reach more accurate population estimates. Here, we specifically explore the use of fluke landmarks learned as attention maps for local feature extraction and without other supervision than the whale IDs. These individual fluke landmarks are then used jointly to predict the whale ID. With this model, we use several techniques to estimate the sensitivity and uncertainty as a function of the consensus level and stability of localisation among the landmarks. For our experiments, we use images of humpback whale flukes provided by the Kaggle Challenge “Humpback Whale Identification” and compare our results to those of a whale expert. |
format |
Article in Journal/Newspaper |
author |
Marcos, Diego Kierdorf, Jana Cheeseman, Ted Tuia, Devis Roscher, Ribana |
author_facet |
Marcos, Diego Kierdorf, Jana Cheeseman, Ted Tuia, Devis Roscher, Ribana |
author_sort |
Marcos, Diego |
title |
A Whale’s Tail - Finding the Right Whale in an Uncertain World |
title_short |
A Whale’s Tail - Finding the Right Whale in an Uncertain World |
title_full |
A Whale’s Tail - Finding the Right Whale in an Uncertain World |
title_fullStr |
A Whale’s Tail - Finding the Right Whale in an Uncertain World |
title_full_unstemmed |
A Whale’s Tail - Finding the Right Whale in an Uncertain World |
title_sort |
whale’s tail - finding the right whale in an uncertain world |
publisher |
Springer |
publishDate |
2022 |
url |
https://research.wur.nl/en/publications/a-whales-tail-finding-theright-whale-inanuncertain-world https://doi.org/10.1007/978-3-031-04083-2_15 |
genre |
Humpback Whale |
genre_facet |
Humpback Whale |
op_source |
xxAI - Beyond Explainable AI - International Workshop, Held in Conjunction with ICML 2020, Revised and Extended Papers ISBN: 9783031040825 |
op_relation |
https://edepot.wur.nl/570250 https://research.wur.nl/en/publications/a-whales-tail-finding-theright-whale-inanuncertain-world doi:10.1007/978-3-031-04083-2_15 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ Wageningen University & Research |
op_doi |
https://doi.org/10.1007/978-3-031-04083-2_15 |
container_start_page |
297 |
op_container_end_page |
313 |
_version_ |
1797584361392963584 |