{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T05:42:49Z","timestamp":1782279769342,"version":"3.54.5"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T00:00:00Z","timestamp":1642118400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T00:00:00Z","timestamp":1642118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001961","name":"AXA Research Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001961","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Pattern Anal Applic"],"published-print":{"date-parts":[[2022,5]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The complexity of state-of-the-art modeling techniques for image classification impedes the ability to explain model predictions in an interpretable way. A counterfactual explanation highlights the parts of an image which, when removed, would change the predicted class. Both legal scholars and data scientists are increasingly turning to counterfactual explanations as these provide a high degree of human interpretability, reveal what minimal information needs to be changed in order to come to a different prediction and do not require the prediction model to be disclosed. Our literature review shows that existing counterfactual methods for image classification have strong requirements regarding access to the training data and the model internals, which often are unrealistic. Therefore, SEDC is introduced as a model-agnostic instance-level explanation method for image classification that does not need access to the training data. As image classification tasks are typically multiclass problems, an additional contribution is the introduction of the SEDC-T method that allows specifying a target counterfactual class. These methods are experimentally tested on ImageNet data, and with concrete examples, we illustrate how the resulting explanations can give insights in model decisions. Moreover, SEDC is benchmarked against existing model-agnostic explanation methods, demonstrating stability of results, computational efficiency and the counterfactual nature of the explanations.<\/jats:p>","DOI":"10.1007\/s10044-021-01055-y","type":"journal-article","created":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T11:02:38Z","timestamp":1642158158000},"page":"315-335","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":66,"title":["Explainable image classification with evidence counterfactual"],"prefix":"10.1007","volume":"25","author":[{"given":"Tom","family":"Vermeire","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dieter","family":"Brughmans","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sofie","family":"Goethals","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raphael Mazzine Barbossa","family":"de Oliveira","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Martens","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,1,14]]},"reference":[{"issue":"11","key":"1055_CR1","doi-asserted-by":"publisher","first-page":"2274","DOI":"10.1109\/TPAMI.2012.120","volume":"34","author":"R Achanta","year":"2012","unstructured":"Achanta R, Shaji A, Smith K, Lucchi A, Fua P, S\u00fcsstrunk S (2012) Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 34(11):2274\u20132282","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1055_CR2","doi-asserted-by":"publisher","first-page":"52138","DOI":"10.1109\/ACCESS.2018.2870052","volume":"6","author":"A Adadi","year":"2018","unstructured":"Adadi A, Berrada M (2018) Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6:52138\u201352160","journal-title":"IEEE Access"},{"key":"1055_CR3","doi-asserted-by":"crossref","unstructured":"Akula AR, Wang S, Zhu SC (2020) Cocox: generating conceptual and counterfactual explanations via fault-lines. In: AAAI, pp 2594\u20132601 (2020)","DOI":"10.1609\/aaai.v34i03.5643"},{"key":"1055_CR4","unstructured":"Alvarez-Melis D, Jaakkola TS (2018) On the robustness of interpretability methods. arXiv preprint arXiv:1806.08049"},{"key":"1055_CR5","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","volume":"58","author":"AB Arrieta","year":"2020","unstructured":"Arrieta AB, D\u00edaz-Rodr\u00edguez N, Del Ser J, Bennetot A, Tabik S, Barbado A, Garc\u00eda S, Gil-L\u00f3pez S, Molina D, Benjamins R et al (2020) Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf Fusion 58:82\u2013115","journal-title":"Inf Fusion"},{"issue":"7","key":"1055_CR6","doi-asserted-by":"publisher","first-page":"e0130140","DOI":"10.1371\/journal.pone.0130140","volume":"10","author":"S Bach","year":"2015","unstructured":"Bach S, Binder A, Montavon G, Klauschen F, M\u00fcller KR, Samek W (2015) On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE 10(7):e0130140","journal-title":"PLoS ONE"},{"key":"1055_CR7","doi-asserted-by":"crossref","unstructured":"Barocas S, Selbst AD, Raghavan M (2019) The hidden assumptions behind counterfactual explanations and principal reasons. arXiv preprint arXiv:1912.04930","DOI":"10.1145\/3351095.3372830"},{"key":"1055_CR8","doi-asserted-by":"crossref","unstructured":"Bertalmio M, Bertozzi AL, Sapiro G (2001) Navier\u2013Stokes, fluid dynamics, and image and video inpainting. In: Proceedings of the 2001 IEEE computer society conference on computer vision and pattern recognition. CVPR 2001, vol 1, pp I\u2013I. IEEE (2001)","DOI":"10.1109\/CVPR.2001.990497"},{"key":"1055_CR9","unstructured":"Brughmans D, Martens D (2021) Nice: an algorithm for nearest instance counterfactual explanations. arXiv preprint arXiv:2104.07411"},{"key":"1055_CR10","doi-asserted-by":"crossref","unstructured":"Byrne RM (2019) Counterfactuals in explainable artificial intelligence (XAI): evidence from human reasoning. In: IJCAI, pp 6276\u20136282","DOI":"10.24963\/ijcai.2019\/876"},{"key":"1055_CR11","unstructured":"Chander A, Srinivasan R, Chelian S, Wang J, Uchino K (2018) Working with beliefs: Ai transparency in the enterprise. In: IUI Workshops (2018)"},{"issue":"3","key":"1055_CR12","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1089\/big.2017.0074","volume":"5","author":"D Chen","year":"2017","unstructured":"Chen D, Fraiberger SP, Moakler R, Provost F (2017) Enhancing transparency and control when drawing data-driven inferences about individuals. Big Data 5(3):197\u2013212","journal-title":"Big Data"},{"key":"1055_CR13","doi-asserted-by":"crossref","unstructured":"Cysneiros LM, Raffi M, do Prado Leite JCS (2018) Software transparency as a key requirement for self-driving cars. In: 2018 IEEE 26th International requirements engineering conference (RE). IEEE, pp 382\u2013387","DOI":"10.1109\/RE.2018.00-21"},{"key":"1055_CR14","doi-asserted-by":"publisher","DOI":"10.3390\/app11167274","author":"RMB de Oliveira","year":"2021","unstructured":"de Oliveira RMB, Martens D (2021) A framework and benchmarking study for counterfactual generating methods on tabular data. Appl Sci. https:\/\/doi.org\/10.3390\/app11167274","journal-title":"Appl Sci"},{"key":"1055_CR15","unstructured":"Dhurandhar A, Chen PY, Luss R, Tu CC, Ting P, Shanmugam K, Das P (2018) Explanations based on the missing: towards contrastive explanations with pertinent negatives. In: Advances in neural information processing systems, pp 592\u2013603 (2018)"},{"key":"1055_CR16","doi-asserted-by":"crossref","unstructured":"Doshi-Velez F, Kortz M, Budish R, Bavitz C, Gershman S, O\u2019Brien D, Schieber S, Waldo J, Weinberger D, Wood A (2017) Accountability of AI under the law: The role of explanation. arXiv preprint arXiv:1711.01134","DOI":"10.2139\/ssrn.3064761"},{"issue":"7639","key":"1055_CR17","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","volume":"542","author":"A Esteva","year":"2017","unstructured":"Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S (2017) Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639):115\u2013118","journal-title":"Nature"},{"issue":"2","key":"1055_CR18","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1023\/B:VISI.0000022288.19776.77","volume":"59","author":"PF Felzenszwalb","year":"2004","unstructured":"Felzenszwalb PF, Huttenlocher DP (2004) Efficient graph-based image segmentation. Int J Comput Vis 59(2):167\u2013181","journal-title":"Int J Comput Vis"},{"key":"1055_CR19","unstructured":"Fernandez C, Provost F, Han X (2020) Explaining data-driven decisions made by AI systems: the counterfactual approach. arXiv preprint arXiv:2001.07417"},{"key":"1055_CR20","doi-asserted-by":"crossref","unstructured":"Fletcher S, Islam MZ (2018) Comparing sets of patterns with the Jaccard index. Australas J Inf Syst 22","DOI":"10.3127\/ajis.v22i0.1538"},{"key":"1055_CR21","doi-asserted-by":"crossref","unstructured":"Goebel R, Chander A, Holzinger K, Lecue F, Akata Z, Stumpf S, Kieseberg P, Holzinger A (2018) Explainable AI: the new 42? In: International cross-domain conference for machine learning and knowledge extraction. Springer, Berlin, pp 295\u2013303 (2018)","DOI":"10.1007\/978-3-319-99740-7_21"},{"key":"1055_CR22","unstructured":"Goodfellow IJ, Shlens J, Szegedy C (2014) Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572"},{"key":"1055_CR23","unstructured":"Goyal Y, Wu Z, Ernst J, Batra D, Parikh D, Lee S (2019) Counterfactual visual explanations. arXiv preprint arXiv:1904.07451"},{"key":"1055_CR24","unstructured":"Gunning D (2017) Explainable artificial intelligence (XAI). Defense Advanced Research Projects Agency (DARPA)"},{"issue":"3","key":"1055_CR25","doi-asserted-by":"publisher","first-page":"723","DOI":"10.1109\/78.80892","volume":"39","author":"RA Haddad","year":"1991","unstructured":"Haddad RA, Akansu AN (1991) A class of fast Gaussian binomial filters for speech and image processing. IEEE Trans Signal Process 39(3):723\u2013727","journal-title":"IEEE Trans Signal Process"},{"key":"1055_CR26","unstructured":"Hendricks LA, Hu R, Darrell T, Akata Z (2018) Generating counterfactual explanations with natural language. arXiv preprint arXiv:1806.09809"},{"key":"1055_CR27","unstructured":"ImageNet: Download (2020). http:\/\/image-net.org\/download"},{"key":"1055_CR28","unstructured":"Joshi S, Koyejo O, Vijitbenjaronk W, Kim B, Ghosh J (2019) Towards realistic individual recourse and actionable explanations in black-box decision making systems. arXiv preprint arXiv:1907.09615"},{"key":"1055_CR29","unstructured":"Karimi AH, Barthe G, Sch\u00f6lkopf B, Valera I (2020) A survey of algorithmic recourse: definitions, formulations, solutions, and prospects. arXiv preprint arXiv:2010.04050"},{"key":"1055_CR30","unstructured":"Lapuschkin S (2019) Opening the machine learning black box with layer-wise relevance propagation. Ph.D. thesis. Technische Universit\u00e4t Berlin"},{"issue":"1","key":"1055_CR31","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.1038\/s41467-019-08987-4","volume":"10","author":"S Lapuschkin","year":"2019","unstructured":"Lapuschkin S, W\u00e4ldchen S, Binder A, Montavon G, Samek W, M\u00fcller KR (2019) Unmasking clever Hans predictors and assessing what machines really learn. Nat Commun 10(1):1096","journal-title":"Nat Commun"},{"issue":"11","key":"1055_CR32","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324","journal-title":"Proc IEEE"},{"issue":"7553","key":"1055_CR33","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444","journal-title":"Nature"},{"key":"1055_CR34","unstructured":"Lee TB (2019) Autopilot was active when a tesla crashed into a truck, killing driver. https:\/\/arstechnica.com\/cars\/2019\/05\/feds-autopilot-was-active-during-deadly-march-tesla-crash\/"},{"key":"1055_CR35","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1017\/S1358246100005130","volume":"27","author":"P Lipton","year":"1990","unstructured":"Lipton P (1990) Contrastive explanation. R Inst Philos Suppl 27:247\u2013266","journal-title":"R Inst Philos Suppl"},{"key":"1055_CR36","unstructured":"Lundberg SM, Lee SI (2017) A unified approach to interpreting model predictions. In: Advances in neural information processing systems, pp 4765\u20134774"},{"issue":"1","key":"1055_CR37","doi-asserted-by":"publisher","first-page":"73","DOI":"10.25300\/MISQ\/2014\/38.1.04","volume":"38","author":"D Martens","year":"2014","unstructured":"Martens D, Provost F (2014) Explaining data-driven document classifications. MIS Q 38(1):73\u201399","journal-title":"MIS Q"},{"key":"1055_CR38","doi-asserted-by":"crossref","unstructured":"Miller T (2018) Explanation in artificial intelligence: insights from the social sciences. Artif Intell","DOI":"10.1016\/j.artint.2018.07.007"},{"key":"1055_CR39","unstructured":"Pawelczyk M, Bielawski S, Van\u00a0den Heuvel J, Richter T, Kasneci G (2021) Carla: a python library to benchmark algorithmic recourse and counterfactual explanation algorithms"},{"key":"1055_CR40","unstructured":"Ramon Y, Martens D, Provost F, Evgeniou T (2019) Counterfactual explanation algorithms for behavioral and textual data. arXiv preprint arXiv:1912.01819"},{"key":"1055_CR41","doi-asserted-by":"crossref","unstructured":"Ribeiro MT, Singh S, Guestrin C (2016) Why should I trust you?: explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. ACM, pp 1135\u20131144","DOI":"10.1145\/2939672.2939778"},{"key":"1055_CR42","doi-asserted-by":"crossref","unstructured":"Samek W, M\u00fcller KR (2019) Towards explainable artificial intelligence. In: Explainable AI: interpreting, explaining and visualizing deep learning. Springer, Berlin, pp 5\u201322 (2019)","DOI":"10.1007\/978-3-030-28954-6_1"},{"key":"1055_CR43","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv 2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4510\u20134520","DOI":"10.1109\/CVPR.2018.00474"},{"key":"1055_CR44","doi-asserted-by":"crossref","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision, pp 618\u2013626","DOI":"10.1109\/ICCV.2017.74"},{"key":"1055_CR45","unstructured":"Shang K (2018) Applying image recognition to insurance. https:\/\/www.soa.org\/globalassets\/assets\/Files\/resources\/research-report\/2018\/applying-image-recognition.pdf"},{"key":"1055_CR46","unstructured":"Simonite T (2018) When it comes to gorillas, google photos remains blind. https:\/\/www.wired.com\/story\/when-it-comes-to-gorillas-google-photos-remains-blind\/"},{"issue":"5","key":"1055_CR47","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1109\/TEVC.2019.2890858","volume":"23","author":"J Su","year":"2019","unstructured":"Su J, Vargas DV, Sakurai K (2019) One pixel attack for fooling deep neural networks. IEEE Trans Evol Comput 23(5):828\u2013841","journal-title":"IEEE Trans Evol Comput"},{"key":"1055_CR48","unstructured":"Szegedy C, Zaremba W, Sutskever I, Bruna J, Erhan D, Goodfellow I, Fergus R (2013) Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199"},{"key":"1055_CR49","unstructured":"Van\u00a0Looveren A, Klaise J (2019) Interpretable counterfactual explanations guided by prototypes. arXiv preprint arXiv:1907.02584"},{"key":"1055_CR50","doi-asserted-by":"crossref","unstructured":"Vedaldi A, Soatto S (2008) Quick shift and kernel methods for mode seeking. In: European conference on computer vision. Springer, Berlin, pp 705\u2013718","DOI":"10.1007\/978-3-540-88693-8_52"},{"key":"1055_CR51","first-page":"841","volume":"31","author":"S Wachter","year":"2017","unstructured":"Wachter S, Mittelstadt B, Russell C (2017) Counterfactual explanations without opening the black box: automated decisions and the GPDR. Harv. JL & Tech 31:841","journal-title":"Harv. JL & Tech"},{"key":"1055_CR52","doi-asserted-by":"crossref","unstructured":"Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: European conference on computer vision. Springer, Berlin, pp 818\u2013833","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"1055_CR53","unstructured":"Zintgraf LM, Cohen TS, Adel T, Welling M (2017) Visualizing deep neural network decisions: Prediction difference analysis arXiv preprint arXiv:1702.04595"}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-021-01055-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10044-021-01055-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-021-01055-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T08:26:19Z","timestamp":1726475179000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10044-021-01055-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,14]]},"references-count":53,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["1055"],"URL":"https:\/\/doi.org\/10.1007\/s10044-021-01055-y","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"value":"1433-7541","type":"print"},{"value":"1433-755X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,14]]},"assertion":[{"value":"20 May 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 December 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 January 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}