{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T04:09:22Z","timestamp":1748664562986,"version":"3.41.0"},"publisher-location":"Cham","reference-count":72,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031926471","type":"print"},{"value":"9783031926488","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-92648-8_18","type":"book-chapter","created":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T16:28:51Z","timestamp":1748622531000},"page":"288-315","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Explanation Alignment: Quantifying the\u00a0Correctness of\u00a0Model Reasoning at Scale"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7213-4241","authenticated-orcid":false,"given":"Hyemin","family":"Bang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9671-5574","authenticated-orcid":false,"given":"Angie","family":"Boggust","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5564-635X","authenticated-orcid":false,"given":"Arvind","family":"Satyanarayan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"18_CR1","unstructured":"Adebayo, J., Gilmer, J., Muelly, M., Goodfellow, I.J., Hardt, M., Kim, B.: Sanity checks for saliency maps. In: Bengio, S., Wallach, H.M., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, 3\u20138 December 2018, Montr\u00e9al, Canada, pp. 9525\u20139536 (2018). https:\/\/proceedings.neurips.cc\/paper\/2018\/hash\/294a8ed24b1ad22ec2e7efea049b8737-Abstract.html"},{"key":"18_CR2","unstructured":"Adebayo, J., Muelly, M., Abelson, H., Kim, B.: Post hoc explanations may be ineffective for detecting unknown spurious correlation. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, 25\u201329 April 2022. OpenReview.net (2022). https:\/\/openreview.net\/forum?id=xNOVfCCvDpM"},{"key":"18_CR3","unstructured":"Aggarwal, M., et al.: Towards trainable saliency maps in medical imaging. CoRR abs\/2011.07482 (2020). https:\/\/arxiv.org\/abs\/2011.07482"},{"key":"18_CR4","unstructured":"Amodei, D., Olah, C., Steinhardt, J., Christiano, P.F., Schulman, J., Man\u00e9, D.: Concrete problems in AI safety. CoRR abs\/1606.06565 (2016). http:\/\/arxiv.org\/abs\/1606.06565"},{"key":"18_CR5","unstructured":"Angwin, J., Larson, J., Mattu, S., Kirchner, L.: Machine bias: there\u2019s software used across the country to predict future criminals. and it\u2019s biased against blacks (2016). https:\/\/www.propublica.org\/article\/machine-bias-risk-assessments-in-criminal-sentencing. Accessed 20 Aug 2024"},{"key":"18_CR6","unstructured":"Arun, N.T., et al.: Assessing the (un)trustworthiness of saliency maps for localizing abnormalities in medical imaging. CoRR abs\/2008.02766 (2020). https:\/\/arxiv.org\/abs\/2008.02766"},{"key":"18_CR7","doi-asserted-by":"publisher","unstructured":"Bellamy, R.K.E., et al.: AI fairness 360: an extensible toolkit for detecting and mitigating algorithmic bias. IBM J. Res. Dev. 63(4\/5), 4:1\u20134:15 (2019). https:\/\/doi.org\/10.1147\/JRD.2019.2942287","DOI":"10.1147\/JRD.2019.2942287"},{"key":"18_CR8","doi-asserted-by":"publisher","unstructured":"Boggust, A., Hoover, B., Satyanarayan, A., Strobelt, H.: Shared interest: measuring human-AI alignment to identify recurring patterns in model behavior. In: Barbosa, S.D.J., et al. (eds.) CHI 2022: CHI Conference on Human Factors in Computing Systems, New Orleans, LA, USA, 29 April 2022\u20135 May 2022, pp. 10:1\u201310:17. ACM (2022). https:\/\/doi.org\/10.1145\/3491102.3501965","DOI":"10.1145\/3491102.3501965"},{"key":"18_CR9","doi-asserted-by":"publisher","unstructured":"Boggust, A.W., Suresh, H., Strobelt, H., Guttag, J.V., Satyanarayan, A.: Saliency cards: a framework to characterize and compare saliency methods. In: Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, FAccT 2023, Chicago, IL, USA, 12\u201315 June 2023, pp. 285\u2013296. ACM (2023). https:\/\/doi.org\/10.1145\/3593013.3593997","DOI":"10.1145\/3593013.3593997"},{"key":"18_CR10","doi-asserted-by":"publisher","unstructured":"Bousselham, W., Boggust, A.W., Chaybouti, S., Strobelt, H., Kuehne, H.: Legrad: an explainability method for vision transformers via feature formation sensitivity. CoRR abs\/2404.03214 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2404.03214","DOI":"10.48550\/ARXIV.2404.03214"},{"key":"18_CR11","unstructured":"Carter, B., Jain, S., Mueller, J., Gifford, D.: Overinterpretation reveals image classification model pathologies. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 15395\u201315407 (2021)"},{"key":"18_CR12","unstructured":"Carter, B., Mueller, J., Jain, S., Gifford, D.K.: What made you do this? Understanding black-box decisions with sufficient input subsets. In: Chaudhuri, K., Sugiyama, M. (eds.) The 22nd International Conference on Artificial Intelligence and Statistics, AISTATS 2019, 16\u201318 April 2019, Naha, Okinawa, Japan, Proceedings of Machine Learning Research, vol.\u00a089, pp. 567\u2013576. PMLR (2019). http:\/\/proceedings.mlr.press\/v89\/carter19a.html"},{"key":"18_CR13","unstructured":"Chang, C., Creager, E., Goldenberg, A., Duvenaud, D.: Explaining image classifiers by counterfactual generation. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, 6\u20139 May 2019. OpenReview.net (2019). https:\/\/openreview.net\/forum?id=B1MXz20cYQ"},{"key":"18_CR14","doi-asserted-by":"publisher","unstructured":"Chefer, H., Gur, S., Wolf, L.: Generic attention-model explainability for interpreting bi-modal and encoder-decoder transformers. In: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, 10\u201317 October 2021, pp. 387\u2013396, IEEE (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00045","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"18_CR15","doi-asserted-by":"publisher","unstructured":"Chefer, H., Gur, S., Wolf, L.: Transformer interpretability beyond attention visualization. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, 19\u201325 June 2021, pp. 782\u2013791. Computer Vision Foundation\/IEEE (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00084. https:\/\/openaccess.thecvf.com\/content\/CVPR2021\/html\/Chefer_Transformer_Interpretability_Beyond_Attention_Visualization_CVPR_2021_paper.html","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"18_CR16","unstructured":"Dastin, J.: Amazon scraps secret AI recruiting tool that showed bias against women (2018). https:\/\/www.reuters.com\/article\/world\/insight-amazon-scraps-secret-ai-recruiting-tool-that-showed-bias-against-women-idUSKCN1MK0AG\/. Accessed 20 Aug 2024"},{"key":"18_CR17","doi-asserted-by":"publisher","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 20\u201325 June 2009, Miami, Florida, USA, pp. 248\u2013255. IEEE Computer Society (2009). https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"18_CR18","doi-asserted-by":"publisher","unstructured":"Deng, L.: The MNIST database of handwritten digit images for machine learning research [best of the web]. IEEE Signal Process. Mag. 29(6), 141\u2013142 (2012). https:\/\/doi.org\/10.1109\/MSP.2012.2211477","DOI":"10.1109\/MSP.2012.2211477"},{"key":"18_CR19","unstructured":"Dooley, S., et al.: Comparing human and machine bias in face recognition. CoRR abs\/2110.08396 (2021). https:\/\/arxiv.org\/abs\/2110.08396"},{"key":"18_CR20","doi-asserted-by":"publisher","unstructured":"Fong, R.C., Vedaldi, A.: Interpretable explanations of black boxes by meaningful perturbation. In: IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, 22\u201329 October 2017, pp. 3449\u20133457. IEEE Computer Society (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.371","DOI":"10.1109\/ICCV.2017.371"},{"issue":"4","key":"18_CR21","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/BF00344251","volume":"36","author":"K Fukushima","year":"1980","unstructured":"Fukushima, K.: Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36(4), 193\u2013202 (1980)","journal-title":"Biol. Cybern."},{"key":"18_CR22","doi-asserted-by":"publisher","unstructured":"Gabriel, I.: Artificial intelligence, values, and alignment. Minds Mach. 30(3), 411\u2013437 (2020). https:\/\/doi.org\/10.1007\/S11023-020-09539-2","DOI":"10.1007\/S11023-020-09539-2"},{"key":"18_CR23","doi-asserted-by":"publisher","unstructured":"Gao, Y., Sun, T.S., Bai, G., Gu, S., Hong, S.R., Zhao, L.: RES: a robust framework for guiding visual explanation. In: Zhang, A., Rangwala, H. (eds.) KDD 2022: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, 14\u201318 August 2022, pp. 432\u2013442. ACM (2022). https:\/\/doi.org\/10.1145\/3534678.3539419","DOI":"10.1145\/3534678.3539419"},{"key":"18_CR24","doi-asserted-by":"publisher","unstructured":"Gao, Y., Sun, T.S., Zhao, L., Hong, S.R.: Aligning eyes between humans and deep neural network through interactive attention alignment. Proc. ACM Hum. Comput. Interact. 6(CSCW2), 1\u201328 (2022). https:\/\/doi.org\/10.1145\/3555590","DOI":"10.1145\/3555590"},{"key":"18_CR25","unstructured":"Geirhos, R., Meding, K., Wichmann, F.A.: Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, 6\u201312 December 2020, virtual (2020). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/9f6992966d4c363ea0162a056cb45fe5-Abstract.html"},{"key":"18_CR26","unstructured":"Geirhos, R., Temme, C.R.M., Rauber, J., Sch\u00fctt, H.H., Bethge, M., Wichmann, F.A.: Generalisation in humans and deep neural networks. In: Bengio, S., Wallach, H.M., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, 3\u20138 December 2018, Montr\u00e9al, Canada, pp. 7549\u20137561 (2018). https:\/\/proceedings.neurips.cc\/paper\/2018\/hash\/0937fb5864ed06ffb59ae5f9b5ed67a9-Abstract.html"},{"key":"18_CR27","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, 27\u201330 June 2016, pp. 770\u2013778. IEEE Computer Society (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"18_CR28","doi-asserted-by":"publisher","unstructured":"Ji, J., et al.: AI alignment: a comprehensive survey. CoRR abs\/2310.19852 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2310.19852","DOI":"10.48550\/ARXIV.2310.19852"},{"key":"18_CR29","doi-asserted-by":"publisher","unstructured":"Kapishnikov, A., Bolukbasi, T., Vi\u00e9gas, F.B., Terry, M.: XRAI: better attributions through regions. In: 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), 27 October\u20132 November 2019, pp. 4947\u20134956. IEEE (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00505","DOI":"10.1109\/ICCV.2019.00505"},{"key":"18_CR30","doi-asserted-by":"publisher","unstructured":"Kim, S.S.Y., Meister, N., Ramaswamy, V.V., Fong, R., Russakovsky, O.: HIVE: evaluating the human interpretability of visual explanations. In: Avidan, S., Brostow, G.J., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022 - Part XII. LNCS, vol. 13672, pp. 280\u2013298. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19775-8_17","DOI":"10.1007\/978-3-031-19775-8_17"},{"key":"18_CR31","unstructured":"Kornblith, S., Norouzi, M., Lee, H., Hinton, G.E.: Similarity of neural network representations revisited. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9\u201315 June 2019, Long Beach, California, USA, Proceedings of Machine Learning Research, vol.\u00a097, pp. 3519\u20133529. PMLR (2019). http:\/\/proceedings.mlr.press\/v97\/kornblith19a.html"},{"key":"18_CR32","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images (2009)"},{"key":"18_CR33","doi-asserted-by":"publisher","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998). https:\/\/doi.org\/10.1109\/5.726791","DOI":"10.1109\/5.726791"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Lee, C.H., Liu, Z., Wu, L., Luo, P.: Maskgan: towards diverse and interactive facial image manipulation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"18_CR35","doi-asserted-by":"publisher","unstructured":"Li, K., Wu, Z., Peng, K., Ernst, J., Fu, Y.: Tell me where to look: guided attention inference network. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, 18\u201322 June 2018, pp. 9215\u20139223. Computer Vision Foundation\/IEEE Computer Society (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00960. http:\/\/openaccess.thecvf.com\/content_cvpr_2018\/html\/Li_Tell_Me_Where_CVPR_2018_paper.html","DOI":"10.1109\/CVPR.2018.00960"},{"key":"18_CR36","doi-asserted-by":"publisher","unstructured":"Linardatos, P., Papastefanopoulos, V., Kotsiantis, S.: Explainable AI: a review of machine learning interpretability methods. Entropy 23(1), 18 (2021). https:\/\/doi.org\/10.3390\/E23010018","DOI":"10.3390\/E23010018"},{"key":"18_CR37","doi-asserted-by":"publisher","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: 2015 IEEE International Conference on Computer Vision, ICCV 2015, Santiago, Chile, 7\u201313 December 2015, pp. 3730\u20133738. IEEE Computer Society (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.425","DOI":"10.1109\/ICCV.2015.425"},{"key":"18_CR38","doi-asserted-by":"publisher","unstructured":"Liu, Z., Mao, H., Wu, C., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, 18\u201324 June 2022, pp. 11966\u201311976. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01167","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"18_CR39","unstructured":"Lundberg, S.M., Lee, S.: A unified approach to interpreting model predictions. In: Guyon, I., von Luxburg, U., Bengio, S., Wallach, H.M., Fergus, R., Vishwanathan, S.V.N., Garnett, R. (eds.) Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4\u20139 December 2017, Long Beach, CA, USA, pp. 4765\u20134774 (2017). https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/8a20a8621978632d76c43dfd28b67767-Abstract.html"},{"key":"18_CR40","unstructured":"Minaee, S., Boykov, Y., Porikli, F., Plaza, A., Kehtarnavaz, N., Terzopoulos, D.: Image segmentation using deep learning: a survey. CoRR abs\/2001.05566 (2020). https:\/\/arxiv.org\/abs\/2001.05566"},{"key":"18_CR41","unstructured":"Molnar, C.: Interpretable Machine Learning, 2 edn (2022). https:\/\/christophm.github.io\/interpretable-ml-book"},{"key":"18_CR42","doi-asserted-by":"publisher","unstructured":"Morrison, K., Mehra, A., Perer, A.: Shared interest...sometimes: understanding the alignment between human perception, vision architectures, and saliency map techniques. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 - Workshops, Vancouver, BC, Canada, 17\u201324 June 2023, pp. 3776\u20133781. IEEE (2023). https:\/\/doi.org\/10.1109\/CVPRW59228.2023.00391","DOI":"10.1109\/CVPRW59228.2023.00391"},{"key":"18_CR43","unstructured":"Muttenthaler, L., Dippel, J., Linhardt, L., Vandermeulen, R.A., Kornblith, S.: Human alignment of neural network representations. In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, 1\u20135 May 2023. OpenReview.net (2023). https:\/\/openreview.net\/forum?id=ReDQ1OUQR0X"},{"issue":"10","key":"18_CR44","doi-asserted-by":"publisher","first-page":"2108","DOI":"10.1016\/j.jid.2018.06.175","volume":"138","author":"A Narla","year":"2018","unstructured":"Narla, A., Kuprel, B., Sarin, K., Novoa, R., Ko, J.: Automated classification of skin lesions: from pixels to practice. J. Investig. Dermatol. 138(10), 2108\u20132110 (2018)","journal-title":"J. Investig. Dermatol."},{"key":"18_CR45","unstructured":"Nguyen, G., Kim, D., Nguyen, A.: The effectiveness of feature attribution methods and its correlation with automatic evaluation scores. In: Ranzato, M., Beygelzimer, A., Dauphin, Y.N., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, 6\u201314 December 2021, virtual, pp. 26422\u201326436 (2021). https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/de043a5e421240eb846da8effe472ff1-Abstract.html"},{"key":"18_CR46","unstructured":"Nguyen, T., Raghu, M., Kornblith, S.: Do wide and deep networks learn the same things? Uncovering how neural network representations vary with width and depth. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, 3\u20137 May 2021. OpenReview.net (2021). https:\/\/openreview.net\/forum?id=KJNcAkY8tY4"},{"key":"18_CR47","unstructured":"Parmar, N., et al.: Image transformer. In: Dy, J.G., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, 10\u201315 July 2018, Proceedings of Machine Learning Research, vol.\u00a080, pp. 4052\u20134061. PMLR (2018). http:\/\/proceedings.mlr.press\/v80\/parmar18a.html"},{"issue":"1","key":"18_CR48","doi-asserted-by":"publisher","first-page":"6268","DOI":"10.1038\/s41598-019-42557-4","volume":"9","author":"F Pasa","year":"2019","unstructured":"Pasa, F., Golkov, V., Pfeiffer, F., Cremers, D., Pfeiffer, D.: Efficient deep network architectures for fast chest x-ray tuberculosis screening and visualization. Sci. Rep. 9(1), 6268 (2019)","journal-title":"Sci. Rep."},{"key":"18_CR49","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Wallach, H.M., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E.B., Garnett, R. (eds.) Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8\u201314 December 2019, Vancouver, BC, Canada, pp. 8024\u20138035 (2019). https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/bdbca288fee7f92f2bfa9f7012727740-Abstract.html"},{"key":"18_CR50","unstructured":"Petsiuk, V., Das, A., Saenko, K.: RISE: randomized input sampling for explanation of black-box models. In: British Machine Vision Conference 2018, BMVC 2018, Newcastle, UK, 3\u20136 September 2018, p. 151. BMVA Press (2018). http:\/\/bmvc2018.org\/contents\/papers\/1064.pdf"},{"key":"18_CR51","doi-asserted-by":"publisher","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R.B., He, K., Doll\u00e1r, P.: Designing network design spaces. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, 13\u201319 June 2020, pp. 10425\u201310433. Computer Vision Foundation\/IEEE (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01044. https:\/\/openaccess.thecvf.com\/content_CVPR_2020\/html\/Radosavovic_Designing_Network_Design_Spaces_CVPR_2020_paper.html","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"18_CR52","unstructured":"Raghu, M., Unterthiner, T., Kornblith, S., Zhang, C., Dosovitskiy, A.: Do vision transformers see like convolutional neural networks? In: Ranzato, M., Beygelzimer, A., Dauphin, Y.N., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, 6\u201314 December 2021, virtual, pp. 12116\u201312128 (2021). https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/652cf38361a209088302ba2b8b7f51e0-Abstract.html"},{"key":"18_CR53","doi-asserted-by":"publisher","unstructured":"Rao, S., B\u00f6hle, M., Parchami-Araghi, A., Schiele, B.: Studying how to efficiently and effectively guide models with explanations. In: IEEE\/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, 1\u20136 October 2023, pp. 1922\u20131933. IEEE (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00184","DOI":"10.1109\/ICCV51070.2023.00184"},{"key":"18_CR54","doi-asserted-by":"publisher","unstructured":"Ribeiro, M.T., Singh, S., Guestrin, C.: \u201cWhy should I trust you?\u201d: explaining the predictions of any classifier. In: Krishnapuram, B., Shah, M., Smola, A.J., Aggarwal, C.C., Shen, D., Rastogi, R. (eds.) Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13\u201317 August 2016, pp. 1135\u20131144. ACM (2016). https:\/\/doi.org\/10.1145\/2939672.2939778","DOI":"10.1145\/2939672.2939778"},{"key":"18_CR55","unstructured":"Rieger, L., Singh, C., Murdoch, W.J., Yu, B.: Interpretations are useful: penalizing explanations to align neural networks with prior knowledge. In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13\u201318 July 2020, Virtual Event, Proceedings of Machine Learning Research, vol. 119, pp. 8116\u20138126. PMLR (2020). http:\/\/proceedings.mlr.press\/v119\/rieger20a.html"},{"key":"18_CR56","doi-asserted-by":"publisher","unstructured":"Ross, A.S., Hughes, M.C., Doshi-Velez, F.: Right for the right reasons: training differentiable models by constraining their explanations. In: Sierra, C. (ed.) Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI 2017, Melbourne, Australia, 19\u201325 August 2017, pp. 2662\u20132670. ijcai.org (2017). https:\/\/doi.org\/10.24963\/IJCAI.2017\/371","DOI":"10.24963\/IJCAI.2017\/371"},{"key":"18_CR57","doi-asserted-by":"publisher","unstructured":"Saporta, A., et al.: Benchmarking saliency methods for chest x-ray interpretation. Nat. Mac. Intell. 4(10), 867\u2013878 (2022). https:\/\/doi.org\/10.1038\/S42256-022-00536-X","DOI":"10.1038\/S42256-022-00536-X"},{"key":"18_CR58","doi-asserted-by":"publisher","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization, vol. 128, pp. 336\u2013359 (2020). https:\/\/doi.org\/10.1007\/S11263-019-01228-7","DOI":"10.1007\/S11263-019-01228-7"},{"key":"18_CR59","doi-asserted-by":"publisher","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. Int. J. Comput. Vis. 128(2), 336\u2013359 (2020). https:\/\/doi.org\/10.1007\/S11263-019-01228-7","DOI":"10.1007\/S11263-019-01228-7"},{"key":"18_CR60","doi-asserted-by":"publisher","unstructured":"Shahriari, K., Shahriari, M.: IEEE standard review - ethically aligned design: a vision for prioritizing human wellbeing with artificial intelligence and autonomous systems. In: IEEE Canada International Humanitarian Technology Conference, IHTC 2017, Toronto, ON, Canada, 21\u201322 July 2017, pp. 197\u2013201. IEEE (2017). https:\/\/doi.org\/10.1109\/IHTC.2017.8058187","DOI":"10.1109\/IHTC.2017.8058187"},{"key":"18_CR61","unstructured":"Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. In: Bengio, Y., LeCun, Y. (eds.) 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, 14\u201316 April 2014, Workshop Track Proceedings (2014). http:\/\/arxiv.org\/abs\/1312.6034"},{"key":"18_CR62","unstructured":"Smilkov, D., Thorat, N., Kim, B., Vi\u00e9gas, F.B., Wattenberg, M.: Smoothgrad: removing noise by adding noise. CoRR abs\/1706.03825 (2017). http:\/\/arxiv.org\/abs\/1706.03825"},{"key":"18_CR63","doi-asserted-by":"publisher","unstructured":"Sucholutsky, I., et al.: Getting aligned on representational alignment. CoRR abs\/2310.13018 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2310.13018","DOI":"10.48550\/ARXIV.2310.13018"},{"key":"18_CR64","unstructured":"Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6\u201311 August 2017, Proceedings of Machine Learning Research, vol.\u00a070, pp. 3319\u20133328. PMLR (2017). http:\/\/proceedings.mlr.press\/v70\/sundararajan17a.html"},{"key":"18_CR65","doi-asserted-by":"publisher","unstructured":"Terry, M., Kulkarni, C., Wattenberg, M., Dixon, L., Morris, M.R.: AI alignment in the design of interactive AI: specification alignment, process alignment, and evaluation support. CoRR abs\/2311.00710 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2311.00710","DOI":"10.48550\/ARXIV.2311.00710"},{"key":"18_CR66","doi-asserted-by":"publisher","unstructured":"Tompson, J., Goroshin, R., Jain, A., LeCun, Y., Bregler, C.: Efficient object localization using convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, 7\u201312 June 2015, pp. 648\u2013656. IEEE Computer Society (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298664","DOI":"10.1109\/CVPR.2015.7298664"},{"key":"18_CR67","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4\u20139 December 2017, Long Beach, CA, USA, pp. 5998\u20136008 (2017). https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"18_CR68","unstructured":"Vellido, A., Mart\u00edn-Guerrero, J.D., Lisboa, P.J.G.: Making machine learning models interpretable. In: 20th European Symposium on Artificial Neural Networks, ESANN 2012, Bruges, Belgium, 25\u201327 April 2012 (2012). https:\/\/www.esann.org\/sites\/default\/files\/proceedings\/legacy\/es2012-7.pdf"},{"key":"18_CR69","doi-asserted-by":"publisher","unstructured":"Wang, Z., Qinami, K., Karakozis, I.C., Genova, K., Nair, P., Hata, K., Russakovsky, O.: Towards fairness in visual recognition: Effective strategies for bias mitigation. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, 13\u201319 June 2020, pp. 8916\u20138925. Computer Vision Foundation\/IEEE (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00894. https:\/\/openaccess.thecvf.com\/content_CVPR_2020\/html\/Wang_Towards_Fairness_in_Visual_Recognition_Effective_Strategies_for_Bias_Mitigation_CVPR_2020_paper.html","DOI":"10.1109\/CVPR42600.2020.00894"},{"key":"18_CR70","doi-asserted-by":"publisher","unstructured":"Wollek, A., et al.: Attention-based saliency maps improve interpretability of pneumothorax classification. CoRR abs\/2303.01871 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2303.01871","DOI":"10.48550\/ARXIV.2303.01871"},{"key":"18_CR71","doi-asserted-by":"publisher","unstructured":"Zhang, J., Bargal, S.A., Lin, Z., Brandt, J., Shen, X., Sclaroff, S.: Top-down neural attention by excitation backprop. Int. J. Comput. Vis. 126(10), 1084\u20131102 (2018). https:\/\/doi.org\/10.1007\/S11263-017-1059-X","DOI":"10.1007\/S11263-017-1059-X"},{"key":"18_CR72","unstructured":"Zhou, C., Ma, X., Michel, P., Neubig, G.: Examining and combating spurious features under distribution shift. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event, Proceedings of Machine Learning Research, vol. 139, pp. 12857\u201312867. PMLR (2021). http:\/\/proceedings.mlr.press\/v139\/zhou21g.html"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-92648-8_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T16:29:30Z","timestamp":1748622570000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-92648-8_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031926471","9783031926488"],"references-count":72,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-92648-8_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}