{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T17:37:26Z","timestamp":1790703446049,"version":"4.1.0"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T00:00:00Z","timestamp":1732579200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T00:00:00Z","timestamp":1732579200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Information & communications Technology Planning & Evaluation","award":["IITP-2020-0-01373"],"award-info":[{"award-number":["IITP-2020-0-01373"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s11263-024-02290-6","type":"journal-article","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T12:38:05Z","timestamp":1732624685000},"page":"2487-2504","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["ICEv2: Interpretability, Comprehensiveness, and Explainability in Vision Transformer"],"prefix":"10.1007","volume":"133","author":[{"given":"Hoyoung","family":"Choi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seungwan","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5535-0081","authenticated-orcid":false,"given":"Kyungsik","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,26]]},"reference":[{"key":"2290_CR1","doi-asserted-by":"crossref","unstructured":"Abnar, S., Zuidema, W. (2020). Quantifying attention flow in transformers. arXiv preprint arXiv:2005.00928","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"2290_CR2","first-page":"23716","volume":"35","author":"J- B Alayrac","year":"2022","unstructured":"Alayrac, J. - B., Donahue, J., Luc, P., Miech, A., Barr, I., & Hasson, Y. (2022). Flamingo: A visual language model for few-shot learning. Advances in Neural Information Processing Systems, 35, 23716\u201323736. others.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2290_CR3","doi-asserted-by":"crossref","unstructured":"Carion, N. , Massa, F. , Synnaeve, G. , Usunier, N. , Kirillov, A. , Zagoruyko, S. (2020). End-to-end object detection with transformers. European conference on computer vision (pp. 213\u2013229).","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2290_CR4","doi-asserted-by":"crossref","unstructured":"Caron, M. , Touvron, H. , Misra, I. , J\u00e9gou, H. , Mairal, J. , Bojanowski, P. , Joulin, A. (2021). Emerging properties in self-supervised vision transformers. Proceedings of the IEEE\/cvf international conference on computer vision (pp. 9650\u20139660).","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"2290_CR5","doi-asserted-by":"crossref","unstructured":"Chefer, H. , Gur, S. , Wolf, L. (2021). Transformer interpretability beyond attention visualization. Proceedings of the IEEE\/cvf conference on computer vision and pattern recognition (pp. 782\u2013791).","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"2290_CR6","first-page":"33618","volume":"35","author":"H Chefer","year":"2022","unstructured":"Chefer, H., Schwartz, I., & Wolf, L. (2022). Optimizing relevance maps of vision transformers improves robustness. Advances in Neural Information Processing Systems, 35, 33618\u201333632.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"2","key":"2290_CR7","doi-asserted-by":"publisher","first-page":"1732","DOI":"10.1109\/TPAMI.2022.3169881","volume":"45","author":"J Choe","year":"2022","unstructured":"Choe, J., Oh, S. J., Chun, S., Lee, S., Akata, Z., & Shim, H. (2022). Evaluation for weakly supervised object localization: Protocol, metrics, and datasets. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(2), 1732\u20131748.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2290_CR8","doi-asserted-by":"crossref","unstructured":"Choe, J. , Oh, S.J. , Lee, S. , Chun, S. , Akata, Z. , Shim, H. (2020) . Evaluating weakly supervised object localization methods right. Proceedings of the IEEE\/cvf conference on computer vision and pattern recognition (pp. 3133\u20133142).","DOI":"10.1109\/CVPR42600.2020.00320"},{"key":"2290_CR9","doi-asserted-by":"crossref","unstructured":"Choe, J. ,Shim, H. (2019). Attention-based dropout layer for weakly supervised object localization. Proceedings of the IEEE\/cvf conference on computer vision and pattern recognition (pp. 2219\u20132228).","DOI":"10.1109\/CVPR.2019.00232"},{"key":"2290_CR10","doi-asserted-by":"crossref","unstructured":"Choi, H. , Jin, S. , Han, K. (2023). Adversarial normalization: I can visualize everything (ice). Proceedings of the IEEE\/cvf conference on computer vision and pattern recognition (pp. 12115\u201312124).","DOI":"10.1109\/CVPR52729.2023.01166"},{"key":"2290_CR11","unstructured":"Dosovitskiy, A. , Beyer, L. , Kolesnikov, A. , Weissenborn, D. , Zhai, X. , Unterthiner, T. et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale . In International conference on learning representations."},{"key":"2290_CR12","first-page":"2416","volume":"2022","author":"C Eichenberg","year":"2022","unstructured":"Eichenberg, C., Black, S., Weinbach, S., Parcalabescu, L., & Frank, A. (2022). Magma-multimodal augmentation of generative models through adapter-based finetuning. Findings of the Association for Computational Linguistics: EMNLP, 2022, 2416\u20132428.","journal-title":"Findings of the Association for Computational Linguistics: EMNLP"},{"key":"2290_CR13","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S. A., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2015). The pascal visual object classes challenge: A retrospective. International Journal of Computer Vision, 111, 98\u2013136.","journal-title":"International Journal of Computer Vision"},{"issue":"2","key":"2290_CR14","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2010). The pascal visual object classes (voc) challenge. International Journal of Computer Vision, 88(2), 303\u2013338.","journal-title":"International Journal of Computer Vision"},{"key":"2290_CR15","doi-asserted-by":"crossref","unstructured":"Gao, W. , Wan, F. , Pan, X. , Peng, Z. , Tian, Q. , Han, Z., Ye, Q. (2021). Ts-cam: Token semantic coupled attention map for weakly supervised object localization. Proceedings of the IEEE\/cvf international conference on computer vision (pp. 2886\u20132895).","DOI":"10.1109\/ICCV48922.2021.00288"},{"key":"2290_CR16","unstructured":"Geirhos, R. , Rubisch, P. , Michaelis, C. , Bethge, M. , Wichmann, F.A. , Brendel, W. (2018). Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness. arXiv preprint arXiv:1811.12231,"},{"key":"2290_CR17","doi-asserted-by":"crossref","unstructured":"Gu, J. , Yang, Y. , Tresp, V. (2018). Understanding individual decisions of cnns via contrastive backpropagation. In Asian conference on computer vision (pp. 119\u2013134).","DOI":"10.1007\/978-3-030-20893-6_8"},{"issue":"3","key":"2290_CR18","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1007\/s11263-014-0713-9","volume":"110","author":"M Guillaumin","year":"2014","unstructured":"Guillaumin, M., K\u00fcttel, D., & Ferrari, V. (2014). Imagenet auto-annotation with segmentation propagation. International Journal of Computer Vision, 110(3), 328\u2013348.","journal-title":"International Journal of Computer Vision"},{"key":"2290_CR19","doi-asserted-by":"publisher","first-page":"11545","DOI":"10.1609\/aaai.v35i13.17374","volume":"35","author":"S Gur","year":"2021","unstructured":"Gur, S., Ali, A., & Wolf, L. (2021). Visualization of supervised and self-supervised neural networks via attribution guided factorization. Proceedings of the AAAI Conference on Artificial Intelligence, 35, 11545\u201311554.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2290_CR20","doi-asserted-by":"crossref","unstructured":"Haurum, J.B., Moeslund, T.B. (2021). Sewer-ml: A multi-label sewer defect classification dataset and benchmark. In Proceedings of the IEEE\/cvf conference on computer vision and pattern recognition (pp. 13456\u201313467).","DOI":"10.1109\/CVPR46437.2021.01325"},{"key":"2290_CR21","doi-asserted-by":"crossref","unstructured":"Iwana, B.K. , Kuroki, R. , Uchida, S. (2019). Explaining convolutional neural networks using softmax gradient layer-wise relevance propagation. In 2019 IEEE\/cvf international conference on computer vision workshop (ICCVW) (pp. 4176\u20134185).","DOI":"10.1109\/ICCVW.2019.00513"},{"key":"2290_CR22","doi-asserted-by":"crossref","unstructured":"Jeon, Y. , Jin, S. , Han, K. (2021). Fancy: Human-centered, deep learning-based framework for fashion style analysis. In Proceedings of the web conference 2021 (pp. 2367\u20132378).","DOI":"10.1145\/3442381.3449833"},{"key":"2290_CR23","doi-asserted-by":"crossref","unstructured":"Kumar\u00a0Singh, K., Jae\u00a0Lee, Y. (2017). Hide-and-seek: Forcing a network to be meticulous for weakly-supervised object and action localization. In Proceedings of the IEEE international conference on computer vision (pp. 3524\u20133533).","DOI":"10.1109\/ICCV.2017.381"},{"key":"2290_CR24","unstructured":"Li, D. , Li, J. , Hoi, S. (2024). Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing. Advances in Neural Information Processing Systems, vol. 36."},{"key":"2290_CR25","unstructured":"Liang, Y. , Chongjian, G. , Tong, Z. , Song, Y. , Wang, J. , Xie, P. (2021). Evit: Expediting vision transformers via token reorganizations. In International conference on learning representations."},{"key":"2290_CR26","first-page":"4765","volume":"30","author":"SM Lundberg","year":"2017","unstructured":"Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4765.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2290_CR27","unstructured":"Luo, Z. , Xi, Y. , Zhang, R. , Vc-gpt, J.M. (2022). Visual conditioned gpt for end-to-end generative vision-and-language pre-training. arXiv preprint arXiv:2201.12723,"},{"key":"2290_CR28","unstructured":"Mokady, R. , Hertz, A. , Bermano, A.H. (2021). Clipcap: Clip prefix for image captioning. arXiv preprint arXiv:2111.09734,"},{"key":"2290_CR29","doi-asserted-by":"publisher","first-page":"2501","DOI":"10.1609\/aaai.v34i03.5632","volume":"34","author":"WJ Nam","year":"2020","unstructured":"Nam, W. J., Gur, S., Choi, J., Wolf, L., & Lee, S. W. (2020). Relative attributing propagation: Interpreting the comparative contributions of individual units in deep neural networks. Proceedings of the AAAI Conference on Artificial Intelligence, 34, 2501\u20132508.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2290_CR30","first-page":"23296","volume":"34","author":"MM Naseer","year":"2021","unstructured":"Naseer, M. M., Ranasinghe, K., Khan, S. H., Hayat, M., Shahbaz Khan, F., & Yang, M. H. (2021). Intriguing properties of vision transformers. Advances in Neural Information Processing Systems, 34, 23296\u201323308.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2290_CR31","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., & Grisel, O. (2011). Scikit-learn: Machine learning in python. The Journal of Machine Learning Research, 12, 2825\u20132830.","journal-title":"The Journal of Machine Learning Research"},{"key":"2290_CR32","doi-asserted-by":"crossref","unstructured":"Pruthi, D. , Gupta, M. , Dhingra, B. , Neubig, G. , Lipton, Z.C. (2019). Learning to deceive with attention-based explanations. arXiv preprint arXiv:1909.07913,","DOI":"10.18653\/v1\/2020.acl-main.432"},{"key":"2290_CR33","unstructured":"Rigotti, M. , Miksovic, C. , Giurgiu, I. , Gschwind, T. , Scotton, P. (2021). Attention-based interpretability with concept transformers. International conference on learning representations."},{"issue":"3","key":"2290_CR34","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., & Ma, S. (2015). Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"2290_CR35","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R. , Cogswell, M. , Das, A. , Vedantam, R. , Parikh, D. , Batra, D. (2017). Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE international conference on computer vision (pp. 618\u2013626).","DOI":"10.1109\/ICCV.2017.74"},{"key":"2290_CR36","doi-asserted-by":"crossref","unstructured":"Shamshad, F. , Khan, S. , Zamir, S.W. , Khan, M.H. , Hayat, M. , Khan, F.S. , Fu, H. (2022). Transformers in medical imaging: A survey. arXiv preprint arXiv:2201.09873,","DOI":"10.1016\/j.media.2023.102802"},{"issue":"4","key":"2290_CR37","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1109\/TPAMI.2015.2465960","volume":"38","author":"J Shi","year":"2015","unstructured":"Shi, J., Yan, Q., Xu, L., & Jia, J. (2015). Hierarchical image saliency detection on extended CSSD. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(4), 717\u2013729.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2290_CR38","unstructured":"Shrikumar, A. , Greenside, P. , Kundaje, A. (2017) . Learning important features through propagating activation differences. International conference on machine learning (pp. 3145\u20133153)."},{"key":"2290_CR39","unstructured":"Shrikumar, A. , Greenside, P. , Shcherbina, A. , Kundaje, A. (2016) Not just a black box: Learning important features through propagating activation differences. arXiv preprint arXiv:1605.01713,"},{"key":"2290_CR40","unstructured":"Sim\u00e9oni, O. , Puy, G. , Vo, H.V. , Roburin, S. , Gidaris, S. , Bursuc, A., Ponce J. (2021). Localized objects with self-supervised transformers and no labels. Bmvc 2021-32nd British machine vision conference."},{"key":"2290_CR41","unstructured":"Smilkov, D. , Thorat, N. , Kim, B. , Vi\u00e9gas, F. , Wattenberg, M. (2017)Smoothgrad: removing noise by adding noise. arXiv preprint arXiv:1706.03825,"},{"key":"2290_CR42","unstructured":"Steiner, A. , Kolesnikov, A. , Zhai, X. , Wightman, R. , Uszkoreit, J. , Beyer, L. (2021)How to train your vit? Data, augmentation, and regularization in vision transformers. arXiv preprint arXiv:2106.10270,"},{"key":"2290_CR43","unstructured":"Sundararajan, M. , Taly, A. , Yan, Q. (2017) Axiomatic attribution for deep networks. In International conference on machine learning (pp. 3319\u20133328)."},{"key":"2290_CR44","unstructured":"Touvron, H. , Cord, M. , Douze, M. , Massa, F. , Sablayrolles, A. , J\u00e9gou, H. (2021)Training data-efficient image transformers & distillation through attention. In International conference on machine learning (pp. 10347\u201310357)."},{"key":"2290_CR45","first-page":"200","volume":"34","author":"M Tsimpoukelli","year":"2021","unstructured":"Tsimpoukelli, M., Menick, J. L., Cabi, S., Eslami, S., Vinyals, O., & Hill, F. (2021). Multimodal few-shot learning with frozen language models. Advances in Neural Information Processing Systems, 34, 200\u2013212.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2290_CR46","unstructured":"Tuli, S. , Dasgupta, I. , Grant, E. , Griffiths, T. (2021)Are convolutional neural networks or transformers more like human vision? Proceedings of the annual meeting of the cognitive science society (vol. 43)."},{"key":"2290_CR47","unstructured":"Ulyanov, D. , Vedaldi, A. , Lempitsky, V. (2016). Instance normalization: The missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022."},{"key":"2290_CR48","first-page":"2017","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30, 2017.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2290_CR49","doi-asserted-by":"crossref","unstructured":"Voita, E. , Talbot, D. , Moiseev, F. , Sennrich, R. , Titov, I. (2019). Analyzing multi-head self-attention: Specialized heads do the heavy lifting, the rest can be pruned.","DOI":"10.18653\/v1\/P19-1580"},{"key":"2290_CR50","unstructured":"Wah, C. , Branson, S. , Welinder, P. , Perona, P. , Belongie, S. (2011). The caltech-ucsd birds-200-2011 dataset."},{"key":"2290_CR51","doi-asserted-by":"crossref","unstructured":"Wang, L. , Lu, H. , Wang, Y. , Feng, M. , Wang, D. , Yin, B. , Ruan, X. (2017). Learning to detect salient objects with image-level supervision. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 136\u2013145).","DOI":"10.1109\/CVPR.2017.404"},{"key":"2290_CR52","doi-asserted-by":"crossref","unstructured":"Wang, Y. , Shen, X. , Hu, S.X. , Yuan, Y. , Crowley, J.L. , Vaufreydaz, D. (2022)Self-supervised transformers for unsupervised object discovery using normalized cut. Proceedings of the IEEE\/cvf conference on computer vision and pattern recognition (pp. 14543\u201314553).","DOI":"10.1109\/CVPR52688.2022.01414"},{"key":"2290_CR53","doi-asserted-by":"crossref","unstructured":"Yang, C. , Zhang, L. , Lu, H. , Ruan, X. , Yang, M- H. (2013)Saliency detection via graph-based manifold ranking. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3166\u20133173).","DOI":"10.1109\/CVPR.2013.407"},{"key":"2290_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, X. , Wei, Y. , Feng, J. , Yang, Y. , Huang, T.S. (2018). Adversarial complementary learning for weakly supervised object localization. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1325\u20131334).","DOI":"10.1109\/CVPR.2018.00144"},{"key":"2290_CR55","doi-asserted-by":"crossref","unstructured":"Zhou, B. , Khosla, A. , Lapedriza, A. , Oliva, A. , Torralba, A. (2016).Learning deep features for discriminative localization. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2921\u20132929).","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02290-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02290-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02290-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T02:00:50Z","timestamp":1744855250000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02290-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,26]]},"references-count":55,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["2290"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02290-6","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,26]]},"assertion":[{"value":"5 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 November 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}