[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124887-en":3,"doc-seo-124887-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},124887,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",8,"Research & Report","Domain-Specific Evaluation of Visual Explanations for Application-Grounded Facial Expression Recognition","Explainable AI in deep learning has generated many visual explanation methods, yet domain-specific ways to judge explanation quality and model performance against application requirements remain limited. This paper introduces a framework for domain-specific evaluation of visual explanations and corresponding robustness assessment. The approach incorporates human expertise into quality criteria and metrics. Applied to facial expression recognition, it delivers application-grounded quality criteria not covered by standard evaluation methods, showing that expert knowledge quality strongly influences precise performance assessment.","Finzel, Bettina; Rieger, Ines; Kuhn, Simon; Schmid, Ute  \nDomain-Specific Evaluation of Visual Explanations for Application-Grounded Facial Expression Recognition  \nDate of secondary publication: 17.05.2024  \nVersion of Record (Published Version), Conferenceobject Persistent identifier: urn:nbn:de:bvb:473-irb-952943  \nPrimary publication  \nFinzel, Bettina; Rieger, Ines; Kuhn, Simon; Schmid, Ute (2023): „Domain-Specific Evaluation of Visual Explanations for Application-Grounded Facial Expression Recognition“. In: A. Holzinger, P. Kieseberg, F. Cabitza, A. Campagner, A. M. Tjoa, E. Weippl (Ed. ), Machine learning and knowledge extraction, Cham, Switzerland: Springer Nature Switzerland, pp. 31–44, doi:  \n10. 1007/978-3-031-40837-3_3.  \nLegal Notice  \nThis work is protected by copyright and/or the indication of a licence. You are free to use this work in any way permitted by the copyright and/or the licence that applies to your usage. For other uses, you must obtain permission from the rights-holders.  \nThis document is made available under a Creative Commons license.  \nThe license information is available online:  \n[https://creativecommons.org/l](https://creativecommons.org/l)icenses/by/4 .0/legalcode  \nDomain-Specific Evaluation of Visual Explanations for Application-Grounded Facial Expression Recognition  \nBettina Finzel (B) , Ines Rieger , Simon Kuhn, and Ute Schmid  \nCognitive Systems, University of Bamberg, Bamberg, Germany {bettina.finzel,ines.rieger,[ute.schmid](ute.schmid}@uni-bamberg.de)[}](ute.schmid}@uni-bamberg.de)[@uni-bamberg.de](ute.schmid}@uni-bamberg.de)  \n[Abstract.](Abstract. Research in the)[ Research in the](Abstract. Research in the) field of explainable artificial intelligence has produced a vast amount of visual explanation methods for deep learningbased image classification in various domains of application. However, there is still a lack of domain-specific evaluation methods to assess an explanation’s quality and a classifier’s performance with respect to domain-specific requirements. In particular, evaluation methods could benefit from integrating human expertise into quality criteria and metrics. Such domain-specific evaluation methods can help to assess the robustness of deep learning models more precisely. In this paper, we present an approach for domain-specific evaluation of visual explanation methods in order to enhance the transparency of deep learning models and estimate their robustness accordingly. As an example use case, we apply our framework to facial expression recognition. We can show that the domain-specific evaluation is especially beneficial for challenging use cases such as facial expression recognition and provides applicationgrounded quality criteria that are not covered by standard evaluation methods. Our comparison of the domain-specific evaluation method with standard approaches thus shows that the quality of the expert knowledge is of great importance for assessing a model’s performance precisely.  \nKeywords: Convolutional Neural Networks · Explainable Artificial Intelligence · Facial Expressions · Explanation Evaluation · Robustness  \n1 Introduction  \nDeep learning approaches are successfully applied for image classification. However, the drawback of these deep learning approaches is their lack of robustness in terms of reliable predictions under small changes in the input data or model parameters [10] . For example, a model should be able to handle out-ofdistribution data that deviate from the training distribution, e.g., by being blurry or showing an object from a different angle. However, often models produce con  \nfidently false  predictions for out-of-distribution data. These can get unnoticed, The work presented in this paper was funded by grant DFG (German Research Foundation) 405630557 (PainFaceReader) .  \n􀀂c The Author(s) 2023  \nA. Holzinger et al. (Eds.): CD-MAKE 2023, LNCS 14065, pp. 31–44, 2023.  \n[https://doi.org/10.1007/978-3-031-40837-3](https://doi.org/10.1007/978-3-031-40837-3_","cbCaiqmcWDLRcsQP","https://ap.wps.com/l/cbCaiqmcWDLRcsQP","pdf",1899920,1,15,"English","en",105,"# Introduction\n## Robustness and Explainability as Trust Enablers\n## Limits of Standard Evaluation for Visual Explanations\n# Domain-Specific Evaluation Framework","[{\"question\":\"Why is domain-specific evaluation needed for visual explanations?\",\"answer\":\"Standard evaluation methods do not provide criteria tailored to application requirements, leaving gaps in how explanation quality and model performance should be judged in specific domains.\"},{\"question\":\"How does the proposed framework incorporate human expertise?\",\"answer\":\"It uses selected expert knowledge and quantifies it automatically by leveraging visual explanations to generate domain-relevant quality criteria and metrics.\"},{\"question\":\"What was the example use case, and what benefit was observed?\",\"answer\":\"The framework was applied to facial expression recognition, where domain-specific evaluation proved especially beneficial for challenging scenarios and produced application-grounded quality criteria beyond standard approaches.\"}]","Domain-Specific Evaluation of Visual Explanations for Application-Grounded Facial Expression Recognition | PDF",1785895232,38,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"domain-specific-evaluation-of-visual-explanations-for-application-grounded-facial-expression-recognition","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/domain-specific-evaluation-of-visual-explanations-for-application-grounded-facial-expression-recognition/124887/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is domain-specific evaluation needed for visual explanations?","Question",{"text":75,"@type":76},"Standard evaluation methods do not provide criteria tailored to application requirements, leaving gaps in how explanation quality and model performance should be judged in specific domains.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed framework incorporate human expertise?",{"text":80,"@type":76},"It uses selected expert knowledge and quantifies it automatically by leveraging visual explanations to generate domain-relevant quality criteria and metrics.",{"name":82,"@type":73,"acceptedAnswer":83},"What was the example use case, and what benefit was observed?",{"text":84,"@type":76},"The framework was applied to facial expression recognition, where domain-specific evaluation proved especially beneficial for challenging scenarios and produced application-grounded quality criteria beyond standard approaches.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]