A Segment-Based Framework for Explainability in Animal Affective Computing

A Segment-Based Framework for Explainability in Animal Affective Computing | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article A Segment-Based Framework for Explainability in Animal Affective Computing Tali Boneh-Shitrit, Annika Bremhorst, Lauren Finka, Daniel S. Mills, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5750275/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 21 Apr, 2025 Read the published version in Scientific Reports → Version 1 posted 6 You are reading this latest preprint version Abstract Recent developments in animal motion tracking and pose recognition have revolutionized the study of animal behavior. More recent efforts extend beyond tracking towards affect recognition using facial and body language analysis, with far-reaching applications in animal welfare and health. Deep learning models are the most commonly used in this context. However, their "black box" nature poses a significant challenge to explainability, which is vital for building trust and encouraging adoption among researchers. Despite its importance, the field of explainability and its quantification remains under-explored. Saliency maps are among the most widely used methods for explainability, where each pixel is assigned a significance level indicating its relevance to the neural network’s decision. Although these maps are frequently used in research, they are predominantly applied qualitatively, with limited methods for quantitatively analyzing them or identifying the most suitable method for a specific task.In this paper, we propose a framework aimed at enhancing explainability in the field of animal affective computing. Assuming the availability of a classifier for a specific affective state and the ability to generate saliency maps, our approach focuses on evaluating and comparing visual explanations by emphasizing the importance of meaningful semantic parts captured as segments, which are thought to be closely linked to behavioral indicators of affective states.Furthermore, our approach introduces a quantitative scoring mechanism to assess how well the saliency maps generated by a given classifier align with predefined semantic regions. This scoring system allows for systematic, measurable comparisons of different pipelines in terms of their visual explanations within animal affective computing. Such a metric can serve as a quality indicator when developing classifiers for known biologically relevant segments or help researchers assess whether a classifier is using expected meaningful regions when exploring new potential indicators.We evaluated the framework using three datasets focused on cat and horse pain and dog emotions. Across all datasets, the generated explanations consistently revealed that the eye area is the most significant feature for the classifiers. These results highlight the potential of the explainability frameworks such as the suggested one to uncover new insights into how machines 'see' animal affective states. Biological sciences/Zoology/Animal behaviour Health sciences/Signs and symptoms/Pain Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 21 Apr, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Accepted 31 Mar, 2025 Reviews received at journal 30 Mar, 2025 Reviewers agreed at journal 27 Mar, 2025 Reviewers invited by journal 27 Mar, 2025 Submission checks completed at journal 26 Mar, 2025 First submitted to journal 23 Mar, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-5750275","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":435039689,"identity":"30fcb3e6-b85d-4f1f-82bc-bcdae70c1a6f","order_by":0,"name":"Tali Boneh-Shitrit","email":"","orcid":"","institution":"University of Haifa","correspondingAuthor":false,"prefix":"","firstName":"Tali","middleName":"","lastName":"Boneh-Shitrit","suffix":""},{"id":435039690,"identity":"12b2dec7-3687-4c6a-9746-fbc51c7b9af9","order_by":1,"name":"Annika Bremhorst","email":"","orcid":"","institution":"Dogs and Science, Zurich, Switzerland","correspondingAuthor":false,"prefix":"","firstName":"Annika","middleName":"","lastName":"Bremhorst","suffix":""},{"id":435039691,"identity":"1a41a586-381a-490a-ba40-13a026441907","order_by":2,"name":"Lauren Finka","email":"","orcid":"","institution":"National Cat Centre, Chelwood Gate","correspondingAuthor":false,"prefix":"","firstName":"Lauren","middleName":"","lastName":"Finka","suffix":""},{"id":435039692,"identity":"4c898e3f-53e2-4bbe-9c58-5516440303f2","order_by":3,"name":"Daniel S. Mills","email":"","orcid":"","institution":"University of Lincoln","correspondingAuthor":false,"prefix":"","firstName":"Daniel","middleName":"S.","lastName":"Mills","suffix":""},{"id":435039693,"identity":"4aa317ea-15bd-46e5-885b-5fa52fd7170d","order_by":4,"name":"Stelio P. Luna","email":"","orcid":"","institution":"S ˜ ao Paulo State University (Unesp)","correspondingAuthor":false,"prefix":"","firstName":"Stelio","middleName":"P.","lastName":"Luna","suffix":""},{"id":435039694,"identity":"716309b4-1640-4531-a503-bb4fdfc7d55f","order_by":5,"name":"Emanuella Dalla Costa","email":"","orcid":"","institution":"University of Milano","correspondingAuthor":false,"prefix":"","firstName":"Emanuella","middleName":"Dalla","lastName":"Costa","suffix":""},{"id":435039695,"identity":"b2ac8f4b-c663-4efa-8e8f-539f39dc75a4","order_by":6,"name":"Anna Zamansky","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8UlEQVRIiWNgGAWjYBADOTYGBiAykINwEwoIazGGajGGajEgrCWxAayFAaqFAY8W/tm9Bz/+qNmW3sd/gO3BjwIDeQb2ww8YHuDRInHnXLKExLHbuW0SCeyGPQYGhg08aQb4HXYjx0DCgA2khYFNgsfgD2MDQw5+v8jfyDH+kfDvdjob0GGSfwwM7Bv43+DXYnAjx0ziYNvtBDaGBDZpHgODxAYJArYYArVYNvbdNmyTSGyTljEwSG6TeGZwAJ8WOaDDbv74dltevv/wMck3fwxs+/mTHz78UYHH+wgA9DgIgGLnAFEaRsEoGAWjYBTgBACZjEjBczyuWAAAAABJRU5ErkJggg==","orcid":"","institution":"University of Haifa","correspondingAuthor":true,"prefix":"","firstName":"Anna","middleName":"","lastName":"Zamansky","suffix":""}],"badges":[],"createdAt":"2025-01-02 08:53:24","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5750275/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5750275/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-96634-y","type":"published","date":"2025-04-21T15:57:16+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":81569603,"identity":"0476b849-8bbd-453f-9a3e-e4bcc78598a6","added_by":"auto","created_at":"2025-04-28 16:07:53","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":906811,"visible":true,"origin":"","legend":"","description":"","filename":"TaliSegmentBasedPaperrevisions2SR.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5750275/v1_covered_e5d84d0c-ba0a-4409-a8f3-1c17704590ec.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Segment-Based Framework for Explainability in Animal Affective Computing","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-5750275/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5750275/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Recent developments in animal motion tracking and pose recognition have revolutionized the study of animal behavior. More recent efforts extend beyond tracking towards affect recognition using facial and body language analysis, with far-reaching applications in animal welfare and health. Deep learning models are the most commonly used in this context. However, their \"black box\" nature poses a significant challenge to explainability, which is vital for building trust and encouraging adoption among researchers. Despite its importance, the field of explainability and its quantification remains under-explored. Saliency maps are among the most widely used methods for explainability, where each pixel is assigned a significance level indicating its relevance to the neural network’s decision. Although these maps are frequently used in research, they are predominantly applied qualitatively, with limited methods for quantitatively analyzing them or identifying the most suitable method for a specific task.In this paper, we propose a framework aimed at enhancing explainability in the field of animal affective computing. Assuming the availability of a classifier for a specific affective state and the ability to generate saliency maps, our approach focuses on evaluating and comparing visual explanations by emphasizing the importance of meaningful semantic parts captured as segments, which are thought to be closely linked to behavioral indicators of affective states.Furthermore, our approach introduces a quantitative scoring mechanism to assess how well the saliency maps generated by a given classifier align with predefined semantic regions. This scoring system allows for systematic, measurable comparisons of different pipelines in terms of their visual explanations within animal affective computing. Such a metric can serve as a quality indicator when developing classifiers for known biologically relevant segments or help researchers assess whether a classifier is using expected meaningful regions when exploring new potential indicators.We evaluated the framework using three datasets focused on cat and horse pain and dog emotions. Across all datasets, the generated explanations consistently revealed that the eye area is the most significant feature for the classifiers. These results highlight the potential of the explainability frameworks such as the suggested one to uncover new insights into how machines 'see' animal affective states.","manuscriptTitle":"A Segment-Based Framework for Explainability in Animal Affective Computing","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-28 07:28:14","doi":"10.21203/rs.3.rs-5750275/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Accepted","date":"2025-03-31T06:18:06+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-03-30T13:50:54+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"319122245859717385755367087369750857639","date":"2025-03-27T21:48:45+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-03-27T09:16:11+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-03-26T06:15:05+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-03-23T18:42:10+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"af4a0205-67f9-4949-95b4-61fffbae5eef","owner":[],"postedDate":"March 28th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":46325736,"name":"Biological sciences/Zoology/Animal behaviour"},{"id":46325737,"name":"Health sciences/Signs and symptoms/Pain"}],"tags":[],"updatedAt":"2025-04-28T16:00:32+00:00","versionOfRecord":{"articleIdentity":"rs-5750275","link":"https://doi.org/10.1038/s41598-025-96634-y","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-04-21 15:57:16","publishedOnDateReadable":"April 21st, 2025"},"versionCreatedAt":"2025-03-28 07:28:14","video":"","vorDoi":"10.1038/s41598-025-96634-y","vorDoiUrl":"https://doi.org/10.1038/s41598-025-96634-y","workflowStages":[]},"version":"v1","identity":"rs-5750275","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5750275","identity":"rs-5750275","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}