{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T08:34:26Z","timestamp":1779352466735,"version":"3.51.4"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030876258","type":"print"},{"value":"9783030876265","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-87626-5_6","type":"book-chapter","created":{"date-parts":[[2021,9,29]],"date-time":"2021-09-29T06:14:35Z","timestamp":1632896075000},"page":"67-79","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Combining Transformer Generators with\u00a0Convolutional Discriminators"],"prefix":"10.1007","author":[{"given":"Ricard","family":"Durall","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stanislav","family":"Frolov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J\u00f6rn","family":"Hees","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Federico","family":"Raue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Franz-Josef","family":"Pfreundt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Dengel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Janis","family":"Keuper","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,30]]},"reference":[{"key":"6_CR1","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv:1607.06450 (2016)"},{"key":"6_CR2","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: International Conference on Learning Representations (2018)"},{"key":"6_CR3","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems (2020)"},{"key":"6_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"6_CR5","unstructured":"Chen, M., et al.: Generative pretraining from pixels. In: International Conference on Machine Learning, pp. 1691\u20131703 (2020)"},{"key":"6_CR6","unstructured":"Coates, A., Ng, A., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. In: Proceedings of the International Conference on Artificial Intelligence and Statistics, pp. 215\u2013223 (2011)"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"6_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Durall, R., Keuper, M., Keuper, J.: Watch your up-convolution: CNN based generative deep neural networks are failing to reproduce spectral distributions. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 7890\u20137899 (2020)","DOI":"10.1109\/CVPR42600.2020.00791"},{"key":"6_CR10","unstructured":"Durall, R., Keuper, M., Pfreundt, F.J., Keuper, J.: Unmasking deepfakes with simple features. arXiv:1911.00686 (2019)"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. arXiv:2012.09841 (2020)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Frolov, S., Hinz, T., Raue, F., Hees, J., Dengel, A.: Adversarial text-to-image synthesis: a review. arXiv:2101.09983 (2021)","DOI":"10.1016\/j.neunet.2021.07.019"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Frolov, S., Sharma, A., Hees, J., Karayil, T., Raue, F., Dengel, A.: AttrLostGAN: attribute controlled image synthesis from reconfigurable layout and style. arXiv:2103.13722 (2021)","DOI":"10.1007\/978-3-030-92659-5_23"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Gong, X., Chang, S., Jiang, Y., Wang, Z.: AutoGAN: neural architecture search for generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3224\u20133234 (2019)","DOI":"10.1109\/ICCV.2019.00332"},{"key":"6_CR15","unstructured":"Goodfellow, I.J., et al.: Generative adversarial networks. In: Advances in Neural Information Processing Systems (2014)"},{"key":"6_CR16","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (GELUs). arXiv:1606.08415 (2016)"},{"key":"6_CR17","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems (2017)"},{"key":"6_CR18","unstructured":"Hudson, D.A., Zitnick, C.L.: Generative adversarial transformers. arXiv:2103.01209 (2021)"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"6_CR20","unstructured":"Jiang, Y., Chang, S., Wang, Z.: TransGAN: two transformers can make one strong GAN. arXiv:2102.07074v2 (2021)"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of StyleGAN. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 8110\u20138119 (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"6_CR23","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: International Conference on Learning Representations (2013)"},{"key":"6_CR24","unstructured":"Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images. Technical report, University of Toronto (2009)"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 4681\u20134690 (2017)","DOI":"10.1109\/CVPR.2017.19"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Lee, C.H., Liu, Z., Wu, L., Luo, P.: MaskGAN: towards diverse and interactive facial image manipulation. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 5549\u20135558 (2020)","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"6_CR27","unstructured":"Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. In: International Conference on Learning Representations (2018)"},{"key":"6_CR28","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: International Conference on Machine Learning (2010)"},{"key":"6_CR29","unstructured":"van den Oord, A., Kalchbrenner, N., Vinyals, O., Espeholt, L., Graves, A., Kavukcuoglu, K.: Conditional image generation with PixelCNN decoders. In: Advances in Neural Information Processing Systems (2016)"},{"key":"6_CR30","unstructured":"van den Oord, A., Vinyals, O., Kavukcuoglu, K.: Neural discrete representation learning. In: Advances in Neural Information Processing Systems (2017)"},{"key":"6_CR31","unstructured":"Parmar, N., et al.: Image transformer. In: International Conference on Machine Learning, pp. 4055\u20134064 (2018)"},{"key":"6_CR32","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: International Conference on Learning Representations (2015)"},{"issue":"8","key":"6_CR33","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"6_CR34","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. arXiv:2102.12092 (2021)"},{"key":"6_CR35","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: International Conference on Machine Learning, pp. 1060\u20131069 (2016)"},{"key":"6_CR36","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: Advances in Neural Information Processing Systems (2016)"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 1874\u20131883 (2016)","DOI":"10.1109\/CVPR.2016.207"},{"key":"6_CR38","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"6_CR39","unstructured":"Van Oord, A., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. In: International Conference on Machine Learning, pp. 1747\u20131756 (2016)"},{"key":"6_CR40","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"6_CR41","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. In: International Conference on Machine Learning, pp. 7354\u20137363 (2019)"}],"container-title":["Lecture Notes in Computer Science","KI 2021: Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87626-5_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T18:23:19Z","timestamp":1673374999000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87626-5_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030876258","9783030876265"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87626-5_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"30 September 2021","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"44","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ki2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ki2021.uni-luebeck.de\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"59","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"16","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}