{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T09:47:16Z","timestamp":1777369636355,"version":"3.51.4"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031666933","type":"print"},{"value":"9783031666940","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-66694-0_10","type":"book-chapter","created":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T06:09:21Z","timestamp":1724306961000},"page":"163-175","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Evolving Deep Architectures: A New Blend of CNNs and Transformers Without Pre-training Dependencies"],"prefix":"10.1007","author":[{"given":"Manu","family":"Kiiskil\u00e4","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6347-9595","authenticated-orcid":false,"given":"Padmasheela","family":"Kiiskil\u00e4","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,21]]},"reference":[{"key":"10_CR1","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/978-1-4842-5364-9_6","volume-title":"Deep Learning with Python: Learn Best Practices of Deep Learning Models with PyTorch","author":"N Ketkar","year":"2021","unstructured":"Ketkar, N., Moolayil, J., Ketkar, N., Moolayil, J.: Convolutional neural networks. In: Ketkar, N., Moolayil, J., Ketkar, N., Moolayil, J. (eds.) Deep Learning with Python: Learn Best Practices of Deep Learning Models with PyTorch, pp. 197\u2013242. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-1-4842-5364-9_6"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Rossolini, G., Nesti, F., D\u2019Amico, G., Nair, S., Biondi, A., Buttazzo, G.: On the real-world adversarial robustness of real-time semantic segmentation models for autonomous driving. IEEE Trans. Neural Netw. Learn. Syst. (2023)","DOI":"10.1109\/TNNLS.2023.3314512"},{"key":"10_CR3","doi-asserted-by":"publisher","first-page":"109228","DOI":"10.1016\/j.patcog.2022.109228","volume":"136","author":"F Yuan","year":"2023","unstructured":"Yuan, F., Zhang, Z., Fang, Z.: An effective CNN and Transformer complementary network for medical image segmentation. Pattern Recogn. 136, 109228 (2023)","journal-title":"Pattern Recogn."},{"issue":"3","key":"10_CR4","doi-asserted-by":"publisher","first-page":"1905","DOI":"10.1007\/s10462-022-10213-5","volume":"56","author":"S Cong","year":"2023","unstructured":"Cong, S., Zhou, Y.: A review of convolutional neural network architectures and their optimizations. Artif. Intell. Rev. 56(3), 1905\u20131969 (2023)","journal-title":"Artif. Intell. Rev."},{"issue":"8","key":"10_CR5","doi-asserted-by":"publisher","first-page":"151","DOI":"10.3390\/computers12080151","volume":"12","author":"M Krichen","year":"2023","unstructured":"Krichen, M.: Convolutional neural networks: a survey. Computers 12(8), 151 (2023)","journal-title":"Computers"},{"key":"10_CR6","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"issue":"5","key":"10_CR7","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.1109\/JAS.2023.123618","volume":"10","author":"T Wu","year":"2023","unstructured":"Wu, T., et al.: A brief overview of ChatGPT: the history, status quo and potential future development. IEEE\/CAA J. Automatica Sinica 10(5), 1122\u20131136 (2023)","journal-title":"IEEE\/CAA J. Automatica Sinica"},{"key":"10_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K.: Google, KT, language, AI: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171\u20134186 (2019)"},{"key":"10_CR9","unstructured":"Radford, A., et al.: Better language models and their implications. OpenAI Blog 1(2) (2019)"},{"key":"10_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth 16\u00a0\u00d7\u00a016 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Shi, R., Li, T., Zhang, L., Yamaguchi, Y.: Visualization comparison of vision transformers and convolutional neural networks. IEEE Trans. Multimed. (2023)","DOI":"10.1109\/TMM.2023.3294805"},{"issue":"9","key":"10_CR12","doi-asserted-by":"publisher","first-page":"5521","DOI":"10.3390\/app13095521","volume":"13","author":"J Maur\u00edcio","year":"2023","unstructured":"Maur\u00edcio, J., Domingues, I., Bernardino, J.: Comparing vision transformers and convolutional neural networks for image classification: a literature review. Appl. Sci. 13(9), 5521 (2023)","journal-title":"Appl. Sci."},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Wang, H.: Traffic sign recognition with vision transformers. In: Proceedings of the 6th International Conference on Information System and Data Mining, pp. 55\u201361 (2022)","DOI":"10.1145\/3546157.3546166"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Hu, R., Singh, A.: Unit: multimodal multitask learning with a unified transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1439\u20131449 (2021)","DOI":"10.1109\/ICCV48922.2021.00147"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Li, F., et al.: Mask dino: towards a unified transformer-based framework for object detection and segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3041\u20133050 (2023)","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Panoptic segformer: delving deeper into panoptic segmentation with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1280\u20131289 (2022)","DOI":"10.1109\/CVPR52688.2022.00134"},{"key":"10_CR17","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: Seg-Former: simple and efficient design for semantic segmentation with transformers. In: Advances in Neural Information Processing Systems, vol. 34, pp. 12077\u201312090 (2021)"},{"key":"10_CR18","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Goncalves, D.N., et al.: MTLSegFormer: multi-task learning with transformers for se-mantic segmentation in precision agriculture. In: Proceedings of the IEEE\/CVF Conf. on Computer Vision and Pattern Recognition, pp. 6289\u20136297 (2023)","DOI":"10.1109\/CVPRW59228.2023.00669"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Mohamed, E., El Sallab, A.: Spatio-temporal multi-task learning transformer for joint moving object detection and segmentation. In: 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), pp. 1470\u20131475. IEEE (2021)","DOI":"10.1109\/ITSC48978.2021.9564969"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Liu, J., Sun, H., Katto, J.: Learned image compression with mixed transformer-CNN architectures. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14388\u201314397 (2023)","DOI":"10.1109\/CVPR52729.2023.01383"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, H., Zhao, M., Zhang, M., Lin, S., Dong, Y., Wang, H.: A combination network of CNN and transformer for interference identification. Front. Comput. Neurosci. 17 (2023)","DOI":"10.3389\/fncom.2023.1309694"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Gillioz, A., Casas, J., Mugellini, E., Abou Khaled, O.: Overview of the transformer-based models for NLP tasks. In: 2020 15th Conference on Computer Science and Information Systems (FedCSIS), pp. 179\u2013183. IEEE (2020)","DOI":"10.15439\/2020F20"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Koco\u0144, J., et al.: ChatGPT: Jack of all trades, master of none. Inf. Fusion 101861 (2023)","DOI":"10.1016\/j.inffus.2023.101861"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: transformer for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7262\u20137272 (2021)","DOI":"10.1109\/ICCV48922.2021.00717"},{"issue":"7","key":"10_CR27","doi-asserted-by":"publisher","first-page":"140","DOI":"10.3390\/jimaging9070140","volume":"9","author":"P Dutta","year":"2023","unstructured":"Dutta, P., Sathi, K.A., Hossain, M.A., Dewan, M.A.A.: Conv-ViT: a convolution and vision transformer-based hybrid feature extraction method for retinal dis-ease detection. J. Imaging 9(7), 140 (2023)","journal-title":"J. Imaging"},{"key":"10_CR28","doi-asserted-by":"publisher","first-page":"106173","DOI":"10.1016\/j.engappai.2023.106173","volume":"123","author":"W Ullah","year":"2023","unstructured":"Ullah, W., Hussain, T., Ullah, F.U.M., Lee, M.Y., Baik, S.W.: TransCNN: hybrid CNN and transformer mechanism for surveillance anomaly detection. Eng. Appl. Artif. Intell. 123, 106173 (2023)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1007\/978-3-030-87193-2_2","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Liu, H., Hu, Q.: TransFuse: fusing transformers and CNNs for medical image segmentation. In: de Bruijne, M., Cattin, P.C., Cotin, S., Padoy, N., Speidel, S., Zheng, Y., Essert, C. (eds.) MICCAI 2021. LNCS, vol. 12901, pp. 14\u201324. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87193-2_2"}],"container-title":["Communications in Computer and Information Science","Deep Learning Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-66694-0_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T06:11:17Z","timestamp":1724307077000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-66694-0_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031666933","9783031666940"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-66694-0_10","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"21 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DeLTA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Deep Learning Theory and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Dijon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","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":"10 July 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 July 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"delta2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/delta.scitevents.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}