{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T23:09:51Z","timestamp":1778800191776,"version":"3.51.4"},"reference-count":61,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.cviu.2026.104773","type":"journal-article","created":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T23:07:16Z","timestamp":1776899236000},"page":"104773","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["RAIN: An embarrassingly simple approach to debiasing attribution evaluation"],"prefix":"10.1016","volume":"268","author":[{"given":"Jiarui","family":"Duan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haofei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4936-4887","authenticated-orcid":false,"given":"Mengqi","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9560-563X","authenticated-orcid":false,"given":"Huiqiong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingli","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2026.104773_b1","doi-asserted-by":"crossref","first-page":"52138","DOI":"10.1109\/ACCESS.2018.2870052","article-title":"Peeking inside the black-box: a survey on explainable artificial intelligence (XAI)","volume":"6","author":"Adadi","year":"2018","journal-title":"IEEE Access"},{"key":"10.1016\/j.cviu.2026.104773_b2","article-title":"Sanity checks for saliency maps","volume":"31","author":"Adebayo","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104773_b3","series-title":"ICLR","article-title":"Towards better understanding of gradient-based attribution methods for deep neural networks","author":"Ancona","year":"2018"},{"key":"10.1016\/j.cviu.2026.104773_b4","doi-asserted-by":"crossref","DOI":"10.1109\/TITS.2025.3574738","article-title":"Safety implications of explainable artificial intelligence in end-to-end autonomous driving","author":"Atakishiyev","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"7","key":"10.1016\/j.cviu.2026.104773_b5","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0130140","article-title":"On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation","volume":"10","author":"Bach","year":"2015","journal-title":"PloS One"},{"key":"10.1016\/j.cviu.2026.104773_b6","series-title":"European Conference on Computer Vision","first-page":"618","article-title":"Rethinking class activation mapping for weakly supervised object localization","author":"Bae","year":"2020"},{"key":"10.1016\/j.cviu.2026.104773_b7","series-title":"Evaluating and aggregating feature-based model explanations","author":"Bhatt","year":"2020"},{"key":"10.1016\/j.cviu.2026.104773_b8","series-title":"European Conference on Computer Vision","first-page":"446","article-title":"Food-101\u2013mining discriminative components with random forests","author":"Bossard","year":"2014"},{"key":"10.1016\/j.cviu.2026.104773_b9","series-title":"2018 IEEE Winter Conference on Applications of Computer Vision","first-page":"839","article-title":"Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks","author":"Chattopadhay","year":"2018"},{"key":"10.1016\/j.cviu.2026.104773_b10","doi-asserted-by":"crossref","unstructured":"Chefer,\u00a0H., Gur,\u00a0S., Wolf,\u00a0L., 2021. Transformer interpretability beyond attention visualization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 782\u2013791.","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"10.1016\/j.cviu.2026.104773_b11","article-title":"This looks like that: deep learning for interpretable image recognition","volume":"32","author":"Chen","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"5","key":"10.1016\/j.cviu.2026.104773_b12","doi-asserted-by":"crossref","first-page":"1091","DOI":"10.1007\/s11263-022-01746-x","article-title":"Deeply explain CNN via hierarchical decomposition","volume":"131","author":"Cheng","year":"2023","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.cviu.2026.104773_b13","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.cviu.2026.104773_b14","series-title":"Towards a rigorous science of interpretable machine learning","author":"Doshi-Velez","year":"2017"},{"key":"10.1016\/j.cviu.2026.104773_b15","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.cviu.2026.104773_b16","doi-asserted-by":"crossref","unstructured":"Fong,\u00a0R., Patrick,\u00a0M., Vedaldi,\u00a0A., 2019. Understanding deep networks via extremal perturbations and smooth masks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 2950\u20132958.","DOI":"10.1109\/ICCV.2019.00304"},{"key":"10.1016\/j.cviu.2026.104773_b17","doi-asserted-by":"crossref","unstructured":"Fong,\u00a0R.C., Vedaldi,\u00a0A., 2017. Interpretable explanations of black boxes by meaningful perturbation. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 3429\u20133437.","DOI":"10.1109\/ICCV.2017.371"},{"key":"10.1016\/j.cviu.2026.104773_b18","series-title":"Distilling a neural network into a soft decision tree","author":"Frosst","year":"2017"},{"key":"10.1016\/j.cviu.2026.104773_b19","series-title":"International Conference on Machine Learning","first-page":"2376","article-title":"Counterfactual visual explanations","author":"Goyal","year":"2019"},{"key":"10.1016\/j.cviu.2026.104773_b20","doi-asserted-by":"crossref","unstructured":"Hartley,\u00a0T., Sidorov,\u00a0K., Willis,\u00a0C., Marshall,\u00a0D., 2020. Explaining failure: Investigation of surprise and expectation in cnns. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops. pp. 12\u201313.","DOI":"10.1109\/CVPRW50498.2020.00014"},{"key":"10.1016\/j.cviu.2026.104773_b21","doi-asserted-by":"crossref","unstructured":"He,\u00a0K., Zhang,\u00a0X., Ren,\u00a0S., Sun,\u00a0J., 2016. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.cviu.2026.104773_b22","article-title":"A benchmark for interpretability methods in deep neural networks","volume":"32","author":"Hooker","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104773_b23","doi-asserted-by":"crossref","unstructured":"Huang,\u00a0Q., Xue,\u00a0M., Huang,\u00a0W., Zhang,\u00a0H., Song,\u00a0J., Jing,\u00a0Y., Song,\u00a0M., 2023. Evaluation and improvement of interpretability for self-explainable part-prototype networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 2011\u20132020.","DOI":"10.1109\/ICCV51070.2023.00192"},{"key":"10.1016\/j.cviu.2026.104773_b24","series-title":"A baseline for Shapley values in MLPs: from missingness to neutrality","author":"Izzo","year":"2021"},{"key":"10.1016\/j.cviu.2026.104773_b25","series-title":"Missingness bias in model debugging","author":"Jain","year":"2022"},{"key":"10.1016\/j.cviu.2026.104773_b26","doi-asserted-by":"crossref","unstructured":"Khakzar,\u00a0A., Khorsandi,\u00a0P., Nobahari,\u00a0R., Navab,\u00a0N., 2022. Do explanations explain? model knows best. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10244\u201310253.","DOI":"10.1109\/CVPR52688.2022.01000"},{"key":"10.1016\/j.cviu.2026.104773_b27","doi-asserted-by":"crossref","unstructured":"Kim,\u00a0J.M., Choe,\u00a0J., Akata,\u00a0Z., Oh,\u00a0S.J., 2021. Keep calm and improve visual feature attribution. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 8350\u20138360.","DOI":"10.1109\/ICCV48922.2021.00824"},{"key":"10.1016\/j.cviu.2026.104773_b28","series-title":"International Conference on Machine Learning","first-page":"2668","article-title":"Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav)","author":"Kim","year":"2018"},{"key":"10.1016\/j.cviu.2026.104773_b29","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.cviu.2026.104773_b30","first-page":"2956","article-title":"Attention guided CAM: Visual explanations of vision transformer guided by self-attention","volume":"vol. 38","author":"Leem","year":"2024"},{"key":"10.1016\/j.cviu.2026.104773_b31","series-title":"Visualizing and understanding neural models in nlp","author":"Li","year":"2015"},{"issue":"1","key":"10.1016\/j.cviu.2026.104773_b32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-022-11012-2","article-title":"Interpretability and fairness evaluation of deep learning models on MIMIC-IV dataset","volume":"12","author":"Meng","year":"2022","journal-title":"Sci. Rep."},{"key":"10.1016\/j.cviu.2026.104773_b33","series-title":"Mimic-if: Interpretability and fairness evaluation of deep learning models on mimic-iv dataset","author":"Meng","year":"2021"},{"key":"10.1016\/j.cviu.2026.104773_b34","series-title":"Interpretable Machine Learning","author":"Molnar","year":"2020"},{"issue":"6","key":"10.1016\/j.cviu.2026.104773_b35","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1002\/cem.873","article-title":"An introduction to decision tree modeling","volume":"18","author":"Myles","year":"2004","journal-title":"J. Chemom.: A J. Chemom. Soc."},{"key":"10.1016\/j.cviu.2026.104773_b36","series-title":"On quantitative aspects of model interpretability","author":"Nguyen","year":"2020"},{"key":"10.1016\/j.cviu.2026.104773_b37","doi-asserted-by":"crossref","unstructured":"Oquab,\u00a0M., Bottou,\u00a0L., Laptev,\u00a0I., Sivic,\u00a0J., 2015. Is object localization for free?-weakly-supervised learning with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 685\u2013694.","DOI":"10.1109\/CVPR.2015.7298668"},{"key":"10.1016\/j.cviu.2026.104773_b38","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104773_b39","series-title":"Rise: Randomized input sampling for explanation of black-box models","author":"Petsiuk","year":"2018"},{"key":"10.1016\/j.cviu.2026.104773_b40","doi-asserted-by":"crossref","unstructured":"Ribeiro,\u00a0M.T., Singh,\u00a0S., Guestrin,\u00a0C., 2016. \u201d Why should i trust you?\u201d Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. pp. 1135\u20131144.","DOI":"10.1145\/2939672.2939778"},{"key":"10.1016\/j.cviu.2026.104773_b41","series-title":"International Conference on Machine Learning","first-page":"18770","article-title":"A consistent and efficient evaluation strategy for attribution methods","author":"Rong","year":"2022"},{"issue":"11","key":"10.1016\/j.cviu.2026.104773_b42","doi-asserted-by":"crossref","first-page":"2660","DOI":"10.1109\/TNNLS.2016.2599820","article-title":"Evaluating the visualization of what a deep neural network has learned","volume":"28","author":"Samek","year":"2016","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"8","key":"10.1016\/j.cviu.2026.104773_b43","doi-asserted-by":"crossref","first-page":"476","DOI":"10.1038\/s42256-020-0212-3","article-title":"Making deep neural networks right for the right scientific reasons by interacting with their explanations","volume":"2","author":"Schramowski","year":"2020","journal-title":"Nat. Mach. Intell."},{"issue":"2","key":"10.1016\/j.cviu.2026.104773_b44","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: Visual explanations from deep networks via gradient-based localization","volume":"128","author":"Selvaraju","year":"2020","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.cviu.2026.104773_b45","series-title":"International Conference on Machine Learning","first-page":"3145","article-title":"Learning important features through propagating activation differences","author":"Shrikumar","year":"2017"},{"key":"10.1016\/j.cviu.2026.104773_b46","series-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"Simonyan","year":"2013"},{"key":"10.1016\/j.cviu.2026.104773_b47","series-title":"Smoothgrad: removing noise by adding noise","author":"Smilkov","year":"2017"},{"key":"10.1016\/j.cviu.2026.104773_b48","series-title":"Striving for simplicity: The all convolutional net","author":"Springenberg","year":"2014"},{"key":"10.1016\/j.cviu.2026.104773_b49","article-title":"Full-gradient representation for neural network visualization","volume":"32","author":"Srinivas","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"10.1016\/j.cviu.2026.104773_b50","doi-asserted-by":"crossref","DOI":"10.23915\/distill.00022","article-title":"Visualizing the impact of feature attribution baselines","volume":"5","author":"Sturmfels","year":"2020","journal-title":"Distill"},{"key":"10.1016\/j.cviu.2026.104773_b51","series-title":"International Conference on Machine Learning","first-page":"3319","article-title":"Axiomatic attribution for deep networks","author":"Sundararajan","year":"2017"},{"key":"10.1016\/j.cviu.2026.104773_b52","series-title":"ICML","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","author":"Sutskever","year":"2013"},{"key":"10.1016\/j.cviu.2026.104773_b53","series-title":"International Conference on Machine Learning","first-page":"6166","article-title":"Adaptive neural trees","author":"Tanno","year":"2019"},{"key":"10.1016\/j.cviu.2026.104773_b54","series-title":"Evaluating explainers via perturbation","author":"Vu","year":"2019"},{"key":"10.1016\/j.cviu.2026.104773_b55","doi-asserted-by":"crossref","first-page":"0771","DOI":"10.34133\/research.0771","article-title":"Dynamic multi-image weighting for automated detection and diagnosis of abnormal urinary tract on voiding cystourethrography with a deep learning system: A retrospective, large-scale, multicenter study","volume":"8","author":"Wu","year":"2025","journal-title":"Research"},{"key":"10.1016\/j.cviu.2026.104773_b56","series-title":"33rd International Joint Conference on Artificial Intelligence, IJCAI-24","article-title":"Protopformer: Concentrating on prototypical parts in vision transformers for interpretable image recognition","author":"Xue","year":"2024"},{"key":"10.1016\/j.cviu.2026.104773_b57","series-title":"European Conference on Computer Vision","first-page":"672","article-title":"Learning propagation rules for attribution map generation","author":"Yang","year":"2020"},{"key":"10.1016\/j.cviu.2026.104773_b58","series-title":"European Conference on Computer Vision","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"Zeiler","year":"2014"},{"key":"10.1016\/j.cviu.2026.104773_b59","first-page":"9623","article-title":"Do feature attribution methods correctly attribute features?","volume":"vol. 36","author":"Zhou","year":"2022"},{"key":"10.1016\/j.cviu.2026.104773_b60","doi-asserted-by":"crossref","unstructured":"Zhou,\u00a0B., Khosla,\u00a0A., Lapedriza,\u00a0A., Oliva,\u00a0A., Torralba,\u00a0A., 2016. Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 2921\u20132929.","DOI":"10.1109\/CVPR.2016.319"},{"key":"10.1016\/j.cviu.2026.104773_b61","series-title":"Visualizing deep neural network decisions: Prediction difference analysis","author":"Zintgraf","year":"2017"}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226001402?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226001402?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T22:32:58Z","timestamp":1778797978000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314226001402"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":61,"alternative-id":["S1077314226001402"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104773","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"RAIN: An embarrassingly simple approach to debiasing attribution evaluation","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104773","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104773"}}