{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T22:01:36Z","timestamp":1757628096687,"version":"3.44.0"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032028129"},{"type":"electronic","value":"9783032028136"}],"license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"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\/978-3-032-02813-6_22","type":"book-chapter","created":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T07:15:44Z","timestamp":1756624544000},"page":"270-277","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Visualizing and\u00a0Interpreting Neural Network Focus Regions: A Comparative Study of\u00a0Vision Transformers on\u00a0Synthetic and\u00a0Real Data"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0939-9317","authenticated-orcid":false,"given":"Denis","family":"Trescher","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8996-3402","authenticated-orcid":false,"given":"Waldemar","family":"Haag","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5383-7837","authenticated-orcid":false,"given":"Enrico","family":"Schr\u00f6der","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,1]]},"reference":[{"key":"22_CR1","doi-asserted-by":"publisher","unstructured":"Abnar, S., Zuidema, W.: Quantifying attention flow in transformers. In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 4190\u20134197. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.385, https:\/\/aclanthology.org\/2020.acl-main.385\/","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"22_CR2","unstructured":"Borrego, J., Dehban, A., Figueiredo, R., Moreno, P., Bernardino, A., Santos-Victor, J.: Applying domain randomization to synthetic data for object category detection. arXiv preprint arXiv:1807.09834 (2018)"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: DETR: end-to-end object detection with transformers (2020). https:\/\/github.com\/facebookresearch\/detr","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Generic attention-model explainability for interpreting bi-modal and encoder-decoder transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 397\u2013406 (2021)","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Transformer interpretability beyond attention visualization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 782\u2013791 (2021)","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"22_CR6","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"22_CR7","unstructured":"Kim, J.H., Choo, W., Song, H.O.: Puzzle mix: exploiting saliency and local statistics for optimal mixup. In: International Conference on Machine Learning, pp. 5275\u20135285. PMLR (2020)"},{"issue":"12","key":"22_CR8","doi-asserted-by":"publisher","first-page":"3197","DOI":"10.1007\/s10115-022-01756-8","volume":"64","author":"X Li","year":"2022","unstructured":"Li, X., et al.: Interpretable deep learning: interpretation, interpretability, trustworthiness, and beyond. Knowl. Inf. Syst. 64(12), 3197\u20133234 (2022)","journal-title":"Knowl. Inf. Syst."},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Peng, X., Saenko, K.: Synthetic to real adaptation with generative correlation alignment networks. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1982\u20131991. IEEE (2018)","DOI":"10.1109\/WACV.2018.00219"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Peterlevitz, A.J., et\u00a0al.: Sim-to-real transfer for object detection in aerial inspections of transmission towers. IEEE Access (2023)","DOI":"10.1109\/ACCESS.2023.3322374"},{"key":"22_CR11","doi-asserted-by":"publisher","unstructured":"Prakash, A., et al.: Structured domain randomization: bridging the reality gap by context-aware synthetic data. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 7249\u20137255 (2019).https:\/\/doi.org\/10.1109\/ICRA.2019.8794443","DOI":"10.1109\/ICRA.2019.8794443"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"22_CR13","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. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 618\u2013626 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.74","DOI":"10.1109\/ICCV.2017.74"},{"key":"22_CR14","doi-asserted-by":"publisher","unstructured":"Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., Abbeel, P.: Domain randomization for transferring deep neural networks from simulation to the real world. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 23\u201330 (2017). https:\/\/doi.org\/10.1109\/IROS.2017.8202133","DOI":"10.1109\/IROS.2017.8202133"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Tremblay, J., et al.: Training deep networks with synthetic data: Bbidging the reality gap by domain randomization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 969\u2013977 (2018)","DOI":"10.1109\/CVPRW.2018.00143"},{"key":"22_CR16","doi-asserted-by":"publisher","unstructured":"Voita, E., Talbot, D., Moiseev, F., Sennrich, R., Titov, I.: Analyzing multi-head self-attention: specialized heads do the heavy lifting, the rest can be pruned. In: Korhonen, A., Traum, D., M\u00e0rquez, L. (eds.) Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 5797\u20135808. Association for Computational Linguistics, Florence (2019). https:\/\/doi.org\/10.18653\/v1\/P19-1580, https:\/\/aclanthology.org\/P19-1580\/","DOI":"10.18653\/v1\/P19-1580"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Vondrick, C., Khosla, A., Malisiewicz, T., Torralba, A.: Hoggles: visualizing object detection features. In: Proceedings of the IEEE International Conference on Computer Vision, pp.\u00a01\u20138 (2013)","DOI":"10.1109\/ICCV.2013.8"},{"key":"22_CR18","first-page":"20929","volume":"34","author":"S Wickramanayake","year":"2021","unstructured":"Wickramanayake, S., Hsu, W., Lee, M.L.: Explanation-based data augmentation for image classification. Adv. Neural. Inf. Process. Syst. 34, 20929\u201320940 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Yeh, C., Chen, Y., Wu, A., Chen, C., Vi\u00e9gas, F., Wattenberg, M.: Attentionviz: a global view of transformer attention. IEEE Trans. Vis. Comput. Graph. (2023)","DOI":"10.1109\/TVCG.2023.3327163"},{"key":"22_CR20","unstructured":"Zagoruyko, S., Komodakis, N.: Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer. In: ICLR (Poster). OpenReview.net (2017). https:\/\/openreview.net\/forum?id=Sks9_ajex"},{"key":"22_CR21","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: International Conference on Learning Representations (2018). https:\/\/openreview.net\/forum?id=r1Ddp1-Rb"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models (2023)","DOI":"10.1109\/ICCV51070.2023.00355"}],"container-title":["Lecture Notes in Computer Science","KI 2025: Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-02813-6_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T06:02:18Z","timestamp":1757484138000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-02813-6_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,1]]},"ISBN":["9783032028129","9783032028136"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-02813-6_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,9,1]]},"assertion":[{"value":"1 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"KI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"German Conference on Artificial Intelligence (K\u00fcnstliche Intelligenz)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Potsdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"16 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"48","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ki2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ki2025.gi.de\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}