{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T17:10:05Z","timestamp":1749661805584,"version":"3.41.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"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":["J Sign Process Syst"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s11265-025-01955-w","type":"journal-article","created":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T08:04:07Z","timestamp":1746605047000},"page":"31-47","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DBiT: A High-Precision Binarized ViT FPGA Accelerator"],"prefix":"10.1007","volume":"97","author":[{"given":"Jun","family":"Gong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3936-0210","authenticated-orcid":false,"given":"Wei","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongxin","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,7]]},"reference":[{"key":"1955_CR1","unstructured":"Vaswani, A., Shazeer, N.M., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I. (2017). Attention is all you need. In: Neural information processing systems. https:\/\/api.semanticscholar.org\/CorpusID:13756489"},{"key":"1955_CR2","doi-asserted-by":"crossref","unstructured":"Pokhrel, S.S.H.O.I. N. (2023). Accelerating image processing using reduced precision calculation convolution engines. In: Journal of signal processing systems","DOI":"10.1007\/s11265-023-01869-5"},{"key":"1955_CR3","doi-asserted-by":"crossref","unstructured":"Xiyu, Q.X.Q.Z. M. (2022). A combined multi-mode visibility detection algorithm based on convolutional neural network. In: Journal of signal processing systems","DOI":"10.1007\/s11265-022-01792-1"},{"key":"1955_CR4","unstructured":"Biderman, S., Schoelkopf, H., Anthony, Q.G., Bradley, H., O\u2019Brien, K., Hallahan, E., Khan, M.A., Purohit, S., Prashanth, U.S., Raff, E., Skowron, A., Sutawika, L., Wal, O. (2023). Pythia: A suite for analyzing large language models across training and scaling. arXiv:2304.01373"},{"key":"1955_CR5","unstructured":"Dettmers, T., Svirschevski, R., Egiazarian, V., Kuznedelev, D., Frantar, E., Ashkboos, S., Borzunov, A., Hoefler, T., Alistarh, D. (2023). Spqr: A sparse-quantized representation for near-lossless llm weight compression. arXiv:2306.03078"},{"key":"1955_CR6","unstructured":"Sun, M., Liu, Z., Bair, A., Kolter, J.Z. (2023). A simple and effective pruning approach for large language models. arXiv:2306.11695"},{"key":"1955_CR7","unstructured":"Chee, J., Cai, Y., Kuleshov, V., Sa, C.D. (2023). Quip: 2-bit quantization of large language models with guarantees. arXiv:2307.13304"},{"key":"1955_CR8","doi-asserted-by":"publisher","unstructured":"Graham, B., El-Nouby, A., Touvron, H., Stock, P., Joulin, A., J\u00e9gou, H., Douze, M. (2021). Levit: a vision transformer in convnet\u2019s clothing for faster inference. In: 2021 IEEE\/CVF International conference on computer vision (ICCV), pp. 12239\u201312249. https:\/\/doi.org\/10.1109\/ICCV48922.2021.01204","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"1955_CR9","unstructured":"Jia, D., Han, K., Wang, Y., Tang, Y., Guo, J., Zhang, C., Tao, D. (2021). Learning efficient vision transformers via fine-grained manifold distillation. In: Neural information processing systems . https:\/\/api.semanticscholar.org\/CorpusID:235731728"},{"key":"1955_CR10","doi-asserted-by":"publisher","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In: 2021 IEEE\/CVF international conference on computer vision (ICCV), pp. 9992\u201310002 . https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1955_CR11","doi-asserted-by":"publisher","unstructured":"Touvron, H., Cord, M., Sablayrolles, A., Synnaeve, G., J\u00e9gou, H. (2021). Going deeper with image transformers. In: 2021 IEEE\/CVF international conference on computer vision (ICCV), pp. 32\u201342 . https:\/\/doi.org\/10.1109\/ICCV48922.2021.00010","DOI":"10.1109\/ICCV48922.2021.00010"},{"issue":"11","key":"1955_CR12","doi-asserted-by":"publisher","first-page":"4088","DOI":"10.1109\/TCAD.2022.3197489","volume":"41","author":"T Wang","year":"2022","unstructured":"Wang, T., Gong, L., Wang, C., Yang, Y., Gao, Y., Zhou, X., & Chen, H. (2022). Via: A novel vision-transformer accelerator based on fpga. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 41(11), 4088\u20134099. https:\/\/doi.org\/10.1109\/TCAD.2022.3197489","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"key":"1955_CR13","doi-asserted-by":"crossref","unstructured":"Gao, S.S.Z.X. C. (2023). Application level resource scheduling for deep learning acceleration on mpsoc. In: Journal of signal processing systems","DOI":"10.1007\/s11265-023-01881-9"},{"key":"1955_CR14","doi-asserted-by":"crossref","unstructured":"Sestito, P.S..S.R. C. (2023). Fpga design of transposed convolutions for deep learning using high-level synthesis. In: Journal of signal processing systems","DOI":"10.1007\/s11265-023-01883-7"},{"key":"1955_CR15","doi-asserted-by":"crossref","unstructured":"Yuan, V.K..O.E. Y. (2023). Accelerating a meta learning model for ultrasonic non-destructive testing applications using model compression and fpga hardware. In: Journal of signal processing systems","DOI":"10.1007\/s11265-023-01901-8"},{"key":"1955_CR16","doi-asserted-by":"crossref","unstructured":"Ali, P.J.T.B. N. (2022). Generating efficient fpga-based cnn accelerators from high-level descriptions. In: Journal of signal processing systems","DOI":"10.1007\/s11265-022-01797-w"},{"key":"1955_CR17","unstructured":"Xi, H., Li, C., Chen, J., Zhu, J. (2023) Training transformers with 4-bit integers. arXiv:2306.11987"},{"key":"1955_CR18","unstructured":"Bhandare, A., Sripathi, V., Karkada, D., Menon, V.V., Choi, S., Datta, K., Saletore, V.A. (2019). Efficient 8-bit quantization of transformer neural machine language translation model. arXiv:1906.00532"},{"key":"1955_CR19","doi-asserted-by":"crossref","unstructured":"Tai, Y.-S., Lin, M.-G., Wu, A. (2023). Tsptq-vit: Two-scaled post-training quantization for vision transformer. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 1\u20135","DOI":"10.1109\/ICASSP49357.2023.10096817"},{"key":"1955_CR20","doi-asserted-by":"crossref","unstructured":"Lin, Y., Zhang, T., Sun, P., Li, Z., Zhou, S. (2021). Fq-vit: Post-training quantization for fully quantized vision transformer. In: International joint conference on artificial intelligence. https:\/\/api.semanticscholar.org\/CorpusID:248300269","DOI":"10.24963\/ijcai.2022\/164"},{"key":"1955_CR21","doi-asserted-by":"crossref","unstructured":"Bondarenko, Y., Nagel, M., Blankevoort, T. (2021). Understanding and overcoming the challenges of efficient transformer quantization. arXiv:2109.12948","DOI":"10.18653\/v1\/2021.emnlp-main.627"},{"key":"1955_CR22","unstructured":"Dettmers, T., Lewis, M., Belkada, Y., Zettlemoyer, L. (2022). Llm.int8(): 8-bit matrix multiplication for transformers at scale. arXiv:2208.07339"},{"key":"1955_CR23","doi-asserted-by":"publisher","unstructured":"Le, P.-H.C., Li, X. (2023). Binaryvit: Pushing binary vision transformers towards convolutional models. In: 2023 IEEE\/CVF conference on computer vision and pattern recognition workshops (CVPRW), pp. 4665\u20134674 . https:\/\/doi.org\/10.1109\/CVPRW59228.2023.00492","DOI":"10.1109\/CVPRW59228.2023.00492"},{"key":"1955_CR24","unstructured":"Liu, Z., O\u011fuz, B., Pappu, A., Xiao, L., Yih, S., Li, M., Krishnamoorthi, R., Mehdad, Y. (2022). Bit: Robustly binarized multi-distilled transformer. arXiv:2205.13016"},{"key":"1955_CR25","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/978-3-031-20053-3_2","volume-title":"Computer Vision - ECCV 2022","author":"S Xu","year":"2022","unstructured":"Xu, S., Li, Y., Wang, T., Ma, T., Zhang, B., Gao, P., Qiao, Y., L\u00fc, J., & Guo, G. (2022). Recurrent bilinear optimization for binary neural networks. In S. Avidan, G. Brostow, M. Ciss\u00e9, G. M. Farinella, & T. Hassner (Eds.), Computer Vision - ECCV 2022 (pp. 19\u201335). Cham: Springer."},{"key":"1955_CR26","doi-asserted-by":"crossref","unstructured":"Le, P.-H.C., Li, X. (2023). Binaryvit: Pushing binary vision transformers towards convolutional models. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 4665\u20134674.","DOI":"10.1109\/CVPRW59228.2023.00492"},{"key":"1955_CR27","doi-asserted-by":"crossref","unstructured":"Li, Y., Xu, S., Lin, M., Cao, X., Liu, C., Sun, X., Zhang, B. (2023). Bi-vit: Pushing the limit of vision transformer quantization. arXiv:2305.12354","DOI":"10.1609\/aaai.v38i4.28109"},{"key":"1955_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wu, B., Luo, W., Yang, X., Liu, W., Cheng, K.T. (2018). Bi-real net: Enhancing the performance of 1-bit cnns with improved representational capability and advanced training algorithm.","DOI":"10.1007\/978-3-030-01267-0_44"},{"key":"1955_CR29","unstructured":"Courbariaux, M., Bengio, Y., David, J.-P. (2015). Binaryconnect: Training deep neural networks with binary weights during propagations. In: Neural information processing systems . https:\/\/api.semanticscholar.org\/CorpusID:1518846"},{"issue":"7","key":"1955_CR30","doi-asserted-by":"publisher","first-page":"2043","DOI":"10.1109\/TNNLS.2018.2876179","volume":"30","author":"S Wu","year":"2019","unstructured":"Wu, S., Li, G., Deng, L., Liu, L., Wu, D., Xie, Y., & Shi, L. (2019). $$l1$$ -norm batch normalization for efficient training of deep neural networks. IEEE Transactions on Neural Networks and Learning Systems, 30(7), 2043\u20132051. https:\/\/doi.org\/10.1109\/TNNLS.2018.2876179","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"1955_CR31","doi-asserted-by":"publisher","unstructured":"Qi, P., Sha, E.H.-M., Zhuge, Q., Peng, H., Huang, S., Kong, Z., Song, Y., Li, B. (2021). Accelerating framework of transformer by hardware design and model compression co-optimization. In: 2021 IEEE\/ACM international conference on computer aided design (ICCAD), pp. 1\u20139. https:\/\/doi.org\/10.1109\/ICCAD51958.2021.9643586","DOI":"10.1109\/ICCAD51958.2021.9643586"},{"key":"1955_CR32","doi-asserted-by":"publisher","unstructured":"Qi, P., Sha, E.H.-M., Zhuge, Q., Peng, H., Huang, S., Kong, Z., Song, Y., Li, B. (2021). Accelerating framework of transformer by hardware design and model compression co-optimization. In: 2021 IEEE\/ACM international conference on computer aided design (ICCAD), pp. 1\u20139. https:\/\/doi.org\/10.1109\/ICCAD51958.2021.9643586","DOI":"10.1109\/ICCAD51958.2021.9643586"},{"key":"1955_CR33","doi-asserted-by":"publisher","unstructured":"Xian, Z., Li, H., Li, Y. (2020). Weight isolation-based binarized neural networks accelerator. In: 2020 IEEE international symposium on circuits and systems (ISCAS), pp. 1\u20134. https:\/\/doi.org\/10.1109\/ISCAS45731.2020.9180405","DOI":"10.1109\/ISCAS45731.2020.9180405"},{"key":"1955_CR34","doi-asserted-by":"crossref","unstructured":"Rastegari, M., Ordonez, V., Redmon, J., Farhadi, A. (2016). Xnor-net: Imagenet classification using binary convolutional neural networks. arXiv:1603.05279","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"1955_CR35","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929"},{"key":"1955_CR36","unstructured":"Hanke, D. (2022). Research on transformer model compression algorithm and hardware accelerator implementation. Master\u2019s thesis, South China University of Technology"},{"key":"1955_CR37","doi-asserted-by":"crossref","unstructured":"Qi, P., Sha, H.M., Zhuge, Q., Peng, H., Huang, S., Kong, Z., Song, Y., Li, B. (2021). Accelerating framework of transformer by hardware design and model compression co-optimization.","DOI":"10.1109\/ICCAD51958.2021.9643586"},{"key":"1955_CR38","doi-asserted-by":"crossref","unstructured":"Ji, Y., Fang, C., Wang, Z. (2024). Beta: Binarized energy-efficient transformer accelerator at the edge. arXiv:2401.11851","DOI":"10.1109\/ISCAS58744.2024.10558636"},{"key":"1955_CR39","doi-asserted-by":"crossref","unstructured":"Li, B., Pandey, S., Fang, H., Lyv, Y., Li, J., Chen, J., Xie, M., Wan, L., Liu, H., Ding, C. (2020). Ftrans: energy-efficient acceleration of transformers using fpga. Proceedings of the ACM\/IEEE International Symposium on Low Power Electronics and Design.","DOI":"10.1145\/3370748.3406567"},{"key":"1955_CR40","doi-asserted-by":"crossref","unstructured":"Peng, H., Huang, S., Geng, T., Li, A., Jiang, W., Liu, H., Wang, S., Ding, C. (2021). Accelerating transformer-based deep learning models on fpgas using column balanced block pruning. In: International symposium on quality electronic design.","DOI":"10.1109\/ISQED51717.2021.9424344"},{"key":"1955_CR41","doi-asserted-by":"crossref","unstructured":"Qi, P., Song, Y., Peng, H., Huang, S., Zhuge, Q., Sha, E.H.M. (2021). Accommodating transformer onto fpga: Coupling the balanced model compression and fpga-implementation optimization. In: GLSVLSI \u201921: great lakes symposium on VLSI 2021","DOI":"10.1145\/3453688.3461739"}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-025-01955-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11265-025-01955-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-025-01955-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T16:50:19Z","timestamp":1749660619000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11265-025-01955-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["1955"],"URL":"https:\/\/doi.org\/10.1007\/s11265-025-01955-w","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"type":"print","value":"1939-8018"},{"type":"electronic","value":"1939-8115"}],"subject":[],"published":{"date-parts":[[2025,2]]},"assertion":[{"value":"13 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 April 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 April 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 May 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}