{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T03:08:25Z","timestamp":1758078505586,"version":"3.44.0"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032050595","type":"print"},{"value":"9783032050601","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-05060-1_11","type":"book-chapter","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T07:58:00Z","timestamp":1758009480000},"page":"123-134","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SimEx-ViT: Explainable Vision Transformer with\u00a0Similarity-Based Attention Modulation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5710-3583","authenticated-orcid":false,"given":"R.","family":"Selventhiran","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4369-6881","authenticated-orcid":false,"given":"Vish","family":"Rajalingam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7550-2641","authenticated-orcid":false,"given":"Satyajit","family":"Das","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,17]]},"reference":[{"key":"11_CR1","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proc. of the Int. Conf. on Neural Information Processing Systems, Long Beach, CA, USA, pp. 6000\u20136010 (2017)"},{"key":"11_CR2","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: Proc. of the Int. Conf. on Learning Representations, pp. 1\u201312 (2021)"},{"key":"11_CR3","unstructured":"Jain, S., Wallace, B.C.: Attention is not explanation. In: Proc. of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1 (Long and Short Papers), Minneapolis, MN, USA, pp. 3543\u20133556 (2019)"},{"key":"11_CR4","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","volume":"58","author":"A Barredo Arrieta","year":"2020","unstructured":"Barredo Arrieta, A., et al.: Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion 58, 82\u2013115 (2020)","journal-title":"Inf. Fusion"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Hao, Y., Dong, L., Wei, F., Xu, K.: Self-attention attribution: interpreting information interactions inside transformer. In: Proc. of the AAAI Conference on Artificial Intelligence, vol. 35, no. 14, pp. 12963\u201312971 (2021)","DOI":"10.1609\/aaai.v35i14.17533"},{"key":"11_CR6","doi-asserted-by":"crossref","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. In: Proc. of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"11_CR7","unstructured":"Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. arXiv (2017)"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Abnar, S., Zuidema, W.: Quantifying attention flow in transformers. In: Proc. of the 58th Annual Meeting of the Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"11_CR9","unstructured":"Achtibat, R., et al.: AttnLRP: attention-aware layer-wise relevance propagation for transformers. arXiv (2024)"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Transformer interpretability beyond attention visualization. In: Proc. of the Computer Vision and Pattern Recognition Conference, Nashville, TN, USA, pp. 782\u2013791 (2021)","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Generic attention-model explainability for interpreting bi-modal and encoder-decoder transformers (2021)","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"11_CR12","doi-asserted-by":"publisher","first-page":"109666","DOI":"10.1016\/j.patcog.2023.109666","volume":"142","author":"L Yu","year":"2023","unstructured":"Yu, L., Xiang, W., Fang, J., Chen, Y.-P.P., Chi, L.: eX-ViT: a novel explainable vision transformer for weakly supervised semantic segmentation. Pattern Recogn. 142, 109666 (2023)","journal-title":"Pattern Recogn."},{"key":"11_CR13","unstructured":"Pan, B., Panda, R., Jiang, Y., Wang, Z., Feris, R., Oliva, A.: IA-RED$$^2$$: interpretability-aware redundancy reduction for vision transformers. In: Advances in Neural Information Processing Systems, vol. 34, pp. 24898\u201324911 (2021)"},{"key":"11_CR14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11263-023-01871-1","volume":"132","author":"H Choi","year":"2024","unstructured":"Choi, H., Jin, S., Han, K.: ICEv2: interpretability, comprehensiveness, and explainability in vision transformer. Int. J. Comput. Vision 132, 1\u201318 (2024)","journal-title":"Int. J. Comput. Vision"},{"key":"11_CR15","unstructured":"Kim, S., Nam, J., Ko, B.C.: ViT-Net: interpretable vision transformers with neural tree decoder. In: Proceedings of the 39th International Conference on Machine Learning (ICML), pp. 11162\u201311172. PMLR (2022)"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"B\u00f6hle, M., Singh, N., Fritz, M., Schiele, B.: B-cos alignment for inherently interpretable CNNs and vision transformers (2024)","DOI":"10.1109\/TPAMI.2024.3355155"},{"key":"11_CR17","unstructured":"Bartunov, S., et al.: Mitigating unintended bias with contextualization: entropy-aware regularization for transformers. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 1101\u20131111 (2020)"},{"issue":"1","key":"11_CR18","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/18.61115","volume":"37","author":"J Lin","year":"1991","unstructured":"Lin, J.: Divergence measures based on the Shannon entropy. IEEE Trans. Inf. Theory 37(1), 145\u2013151 (1991)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: transformer for semantic segmentation. In: Proc. of the International Conference on Computer Vision, pp. 510\u2013520 (2021)","DOI":"10.1109\/ICCV48922.2021.00717"}],"container-title":["Lecture Notes in Computer Science","Computer Analysis of Images and Patterns"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-05060-1_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T07:58:08Z","timestamp":1758009488000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05060-1_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,17]]},"ISBN":["9783032050595","9783032050601"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05060-1_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,17]]},"assertion":[{"value":"17 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CAIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Analysis of Images and Patterns","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Las Palmas de Gran Canaria","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"caip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/caip2025.com","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}