{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:14:53Z","timestamp":1783437293875,"version":"3.54.6"},"reference-count":24,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,4,13]],"date-time":"2025-04-13T00:00:00Z","timestamp":1744502400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Science Foundation of China (NSFC)","award":["62271514"],"award-info":[{"award-number":["62271514"]}]},{"name":"National Science Foundation of China (NSFC)","award":["JCYJ20210324120002007"],"award-info":[{"award-number":["JCYJ20210324120002007"]}]},{"name":"National Science Foundation of China (NSFC)","award":["2023B1212010011"],"award-info":[{"award-number":["2023B1212010011"]}]},{"name":"National Science Foundation of China (NSFC)","award":["HPKF202403"],"award-info":[{"award-number":["HPKF202403"]}]},{"name":"National Science Foundation of China (NSFC)","award":["HPKF202402"],"award-info":[{"award-number":["HPKF202402"]}]},{"name":"Science, Technology and Innovation Commission of Shenzhen Municipality","award":["62271514"],"award-info":[{"award-number":["62271514"]}]},{"name":"Science, Technology and Innovation Commission of Shenzhen Municipality","award":["JCYJ20210324120002007"],"award-info":[{"award-number":["JCYJ20210324120002007"]}]},{"name":"Science, Technology and Innovation Commission of Shenzhen Municipality","award":["2023B1212010011"],"award-info":[{"award-number":["2023B1212010011"]}]},{"name":"Science, Technology and Innovation Commission of Shenzhen Municipality","award":["HPKF202403"],"award-info":[{"award-number":["HPKF202403"]}]},{"name":"Science, Technology and Innovation Commission of Shenzhen Municipality","award":["HPKF202402"],"award-info":[{"award-number":["HPKF202402"]}]},{"name":"Open Project of Guangdong Provincial Key Laboratory of Intelligent PortSecurity Inspection","award":["62271514"],"award-info":[{"award-number":["62271514"]}]},{"name":"Open Project of Guangdong Provincial Key Laboratory of Intelligent PortSecurity Inspection","award":["JCYJ20210324120002007"],"award-info":[{"award-number":["JCYJ20210324120002007"]}]},{"name":"Open Project of Guangdong Provincial Key Laboratory of Intelligent PortSecurity Inspection","award":["2023B1212010011"],"award-info":[{"award-number":["2023B1212010011"]}]},{"name":"Open Project of Guangdong Provincial Key Laboratory of Intelligent PortSecurity Inspection","award":["HPKF202403"],"award-info":[{"award-number":["HPKF202403"]}]},{"name":"Open Project of Guangdong Provincial Key Laboratory of Intelligent PortSecurity Inspection","award":["HPKF202402"],"award-info":[{"award-number":["HPKF202402"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>The Transformer-based target detection model, DETR, has powerful feature extraction and recognition capabilities, but its high computational and storage requirements limit its deployment on resource-constrained devices. To solve this problem, we first replace the ResNet-50 backbone network in DETR with Swin-T, which realizes the unification of the backbone network with the Transformer encoder and decoder under the same Transformer processing paradigm. On this basis, we propose a quantized inference scheme based entirely on integers, which effectively serves as a data compression method for reducing memory occupation and computational complexity. Unlike previous approaches that only quantize the linear layer of DETR, we further apply integer approximation to all non-linear operational layers (e.g., Sigmoid, Softmax, LayerNorm, GELU), thus realizing the execution of the entire inference process in the integer domain. Experimental results show that our method reduces the computation and storage to 6.3% and 25% of the original model, respectively, while the average accuracy decreases by only 1.1%, which validates the effectiveness of the method as an efficient and hardware-friendly solution for target detection.<\/jats:p>","DOI":"10.3390\/e27040422","type":"journal-article","created":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T06:18:36Z","timestamp":1744611516000},"page":"422","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Efficient Integer Quantization for Compressed DETR Models"],"prefix":"10.3390","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6846-830X","authenticated-orcid":false,"given":"Peng","family":"Liu","sequence":"first","affiliation":[{"name":"The School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen 518000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Congduan","family":"Li","sequence":"additional","affiliation":[{"name":"The School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen 518000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nanfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Intelligent Port Security Inspection, Huangpu Customs District, Guangzhou 510700, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingfeng","family":"Yang","sequence":"additional","affiliation":[{"name":"Guangzhou Institute of Industrial Intelligence, Guangzhou 511458, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5986-7184","authenticated-orcid":false,"given":"Li","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Beiyangyuan Campus, Tianjin 300354, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,4,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"15407","DOI":"10.1109\/TITS.2024.3439557","article-title":"Robustness-aware 3D object detection in autonomous driving: A review and outlook","volume":"25","author":"Song","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Al-E\u2019mari, S., Sanjalawe, Y., and Alqudah, H. (2024, January 26\u201328). Integrating enhanced security protocols with moving object detection: A YOLO-based approach for real-time surveillance. Proceedings of the 2nd International Conference on Cyber Resilience (ICCR), Dubai, United Arab Emirates.","DOI":"10.1109\/ICCR61006.2024.10532863"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"57815","DOI":"10.1109\/ACCESS.2024.3386826","article-title":"A comprehensive systematic review of YOLO for medical object detection (2018 to 2023)","volume":"12","author":"Ragab","year":"2024","journal-title":"IEEE Access"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"40017","DOI":"10.1109\/JSEN.2024.3478810","article-title":"Enhancing smart agriculture with lightweight object detection: MobileNetv3-YOLOv4 and adaptive width multipliers","volume":"24","author":"Lin","year":"2024","journal-title":"IEEE Sens. J."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., and Zitnick, C.L. (2014, January 6\u201312). Microsoft COCO: Common objects in context. Proceedings of the 13th European Conference on Computer Vision (ECCV), Zurich, Switzerland. Part V.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref_6","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention is all you need. Proceedings of the 31st Conference on Neural Information Processing Systems (NeurIPS), Long Beach, CA, USA."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S. (2020, January 23\u201328). End-to-end object detection with transformers. Proceedings of the 16th European Conference on Computer Vision (ECCV), Glasgow, UK.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref_8","unstructured":"Liu, Z., Wang, Y., Han, K., Zhang, W., Ma, S., and Gao, W. (2021, January 6\u201314). Post-training quantization for vision transformer. Proceedings of the Advances in Neural Information Processing Systems 34 (NeurIPS 2021), Online."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., Adam, H., and Kalenichenko, D. (2018, January 18\u201322). Quantization and training of neural networks for efficient integer-arithmetic-only inference. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Xu, S., Li, Y., Lin, M., Gao, P., Guo, G., Lu, J., and Zhang, B. (2023, January 18\u201322). Q-DETR: An efficient low-bit quantized detection transformer. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00374"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wu, Z., Lu, J., and Zhou, J. (2020, January 14\u201319). BiDet: An efficient binarized object detector. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00212"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ding, Y., Feng, W., Chen, C., Guo, J., and Liu, X. (2024, January 17\u201318). Reg-PTQ: Regression-specialized post-training quantization for fully quantized object detector. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01531"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Li, R., Wang, Y., Liang, F., Qin, H., Yan, J., and Fan, R. (2019, January 15\u201320). Fully quantized network for object detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00292"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Wei, Y., Pan, X., Qin, H., Ouyang, W., and Yan, J. (2018, January 8\u201314). Quantization mimic: Towards very tiny CNN for object detection. Proceedings of the 15th European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01237-3_17"},{"key":"ref_15","unstructured":"Yang, L., Zhang, T., Sun, P., Li, Z., and Zhou, S. (2022, January 23\u201329). FQ-ViT: Post-training quantization for fully quantized vision transformer. Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI), Vienna, Austria."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Li, Z., and Gu, Q. (2023, January 2\u20133). I-ViT: Integer-only quantization for efficient vision transformer inference. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France.","DOI":"10.1109\/ICCV51070.2023.01565"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Li, Z., Xiao, J., Yang, L., and Gu, Q. (2023, January 2\u20133). RepQViT: Scale reparameterization for post-training quantization of vision transformers. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France.","DOI":"10.1109\/ICCV51070.2023.01580"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"He, Y., Lou, Z., Zhang, L., Liu, J., Wu, W., Zhou, H., and Zhuang, B. (2023, January 2\u20133). BiViT: Extremely compressed binary vision transformers. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France.","DOI":"10.1109\/ICCV51070.2023.00520"},{"key":"ref_19","unstructured":"Kim, S., Gholami, A., Yao, Z., Mahoney, M.W., and Keutzer, K. (2021, January 8\u201324). I-BERT: Integer-only BERT quantization. Proceedings of the International Conference on Machine Learning (ICML), Virtual Event."},{"key":"ref_20","unstructured":"Bengio, Y., L\u00e9onard, N., and Courville, A. (2013). Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv."},{"key":"ref_21","unstructured":"Hendrycks, D., and Gimpel, K. (2016). Gaussian error linear units (GELUs). arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Lin, Y., Li, Y., Liu, T., Xiao, T., Liu, T., and Zhu, J. (2021, January 19\u201327). Towards fully 8-bit integer inference for the transformer model. Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI), Montreal, QC, Canada.","DOI":"10.24963\/ijcai.2020\/520"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"17227","DOI":"10.1109\/TNNLS.2023.3301007","article-title":"PSAQ-ViT v2: Toward accurate and general data-free quantization for vision transformers","volume":"35","author":"Li","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_24","unstructured":"van Baalen, M., Louizos, C., Nagel, M., Amjad, R.A., Wang, Y., Blankevoort, T., and Welling, M. (2020, January 6\u201312). Bayesian bits: Unifying quantization and pruning. Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS), Online."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/27\/4\/422\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:13:38Z","timestamp":1760030018000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/27\/4\/422"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,13]]},"references-count":24,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["e27040422"],"URL":"https:\/\/doi.org\/10.3390\/e27040422","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,13]]}}}