{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T04:40:34Z","timestamp":1777696834650,"version":"3.51.4"},"reference-count":42,"publisher":"SAGE Publications","issue":"6","license":[{"start":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T00:00:00Z","timestamp":1742342400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["No.ZR2022MF260"],"award-info":[{"award-number":["No.ZR2022MF260"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Intelligent Data Analysis: An International Journal"],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:p>Knowledge distillation has shown its potential in the field of computer vision, significantly reducing model parameters and memory usage with minimal impact on model performance. Although current mainstream methods face issues related to inconsistencies between distillation targets and real targets, as well as insufficient learning of teacher features. To address these issues, this paper presents a novel knowledge distillation framework, termed ADKD, designed to mitigate the limitations of current methodologies. It consists of two modules: AGD (Adaptive Generative Distillation) and RHD (Reused Head Distillation). Through AGD, the teacher guides the learning of student network, enabling student to achieve stronger representational power. Meanwhile, RHD effectively addresses the discrepancies between real targets and distillation targets. By masking and reusing feature maps and utilizing the teacher detection head, a more effective object detection model is obtained. The proposed approach is straightforward to implement and effective, having undergone extensive experimentation on datasets PASCAL VOC and MS COCO to demonstrate its efficacy. The results indicate that our method outperforms other knowledge distillation techniques.<\/jats:p>","DOI":"10.1177\/1088467x251325364","type":"journal-article","created":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T12:04:49Z","timestamp":1742385889000},"page":"1536-1548","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive generative knowledge distillation for dense object detection with reused detector"],"prefix":"10.1177","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2255-7877","authenticated-orcid":false,"given":"Hong","family":"Liang","sequence":"first","affiliation":[{"name":"Qingdao Institute of Software, College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, Shandong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1804-9834","authenticated-orcid":false,"given":"Shuaiqing","family":"Wang","sequence":"additional","affiliation":[{"name":"Qingdao Institute of Software, College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, Shandong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0782-5263","authenticated-orcid":false,"given":"Qian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Qingdao Institute of Software, College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, Shandong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingwen","family":"Shao","sequence":"additional","affiliation":[{"name":"Qingdao Institute of Software, College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, Shandong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2025,3,19]]},"reference":[{"key":"e_1_3_4_2_2","unstructured":"Wang T Yuan L Zhang X et al. Distilling object detectors with fine-grained feature imitation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition Vol. 30 2019 pp.4933\u20134942. (Curran Associates Inc. 2017)."},{"key":"e_1_3_4_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3248612"},{"key":"e_1_3_4_4_2","first-page":"5700","article-title":"Transform quantization for cnn compression","volume":"44","author":"Young SI","year":"2021","unstructured":"Young SI, Zhe W, Taubman D, et al. Transform quantization for cnn compression. IEEE Trans Pattern Anal Mach Intell 2021; 44: 5700\u20135714.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"e_1_3_4_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.02.035"},{"key":"e_1_3_4_6_2","unstructured":"Hinton G Vinyals O Dean J. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 2015."},{"key":"e_1_3_4_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3257546"},{"key":"e_1_3_4_8_2","unstructured":"Romero A et al. Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550 2014."},{"key":"e_1_3_4_9_2","unstructured":"Zheng Z et al. Localization distillation for dense object detection. 2022 pp.9407\u20139416."},{"key":"e_1_3_4_10_2","first-page":"15394","article-title":"PKD: general distillation framework for object detectors via pearson correlation coefficient","volume":"35","author":"Cao W","year":"2022","unstructured":"Cao W, et al. PKD: general distillation framework for object detectors via pearson correlation coefficient. Adv Neural Inf Process Syst 2022; 35: 15394\u201315406.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_11_2","doi-asserted-by":"crossref","unstructured":"Yang Z et al. Masked generative distillation. In: European conference on computer Vision 2022 pp.53\u201369. Springer.","DOI":"10.1007\/978-3-031-20083-0_4"},{"key":"e_1_3_4_12_2","doi-asserted-by":"crossref","unstructured":"Wang J et al. CROSSKD: cross-head knowledge distillation for object detection. 2024 pp.16520\u201316530.","DOI":"10.1109\/CVPR52733.2024.01563"},{"key":"e_1_3_4_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"e_1_3_4_14_2","doi-asserted-by":"crossref","unstructured":"Lin T-Y et al. Microsoft COCO: common objects in context. 2014 pp.740\u2013755. Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_4_15_2","first-page":"21002","article-title":"Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection","volume":"33","author":"Li X","year":"2020","unstructured":"Li X, et al. Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection. Adv Neural Inf Process Syst 2020; 33: 21002\u201321012.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_16_2","doi-asserted-by":"crossref","unstructured":"Lin T-Y Goyal P Girshick R et al. Focal loss for dense object detection. 2017 pp.2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_4_17_2","doi-asserted-by":"crossref","unstructured":"Zhang S Chi C Yao Y et al. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. 2020 pp.9759\u20139768.","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"e_1_3_4_18_2","doi-asserted-by":"crossref","unstructured":"Girshick R Donahue J Darrell T et al. Rich feature hierarchies for accurate object detection and semantic segmentation. 2014 pp.580\u2013587.","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_3_4_19_2","doi-asserted-by":"crossref","unstructured":"He K Gkioxari G Doll\u00e1r P et al. Mask r-cnn. 2017 pp.2961\u20132969.","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_4_20_2","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume":"39","author":"Ren S","year":"2016","unstructured":"Ren S, He K, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 2016; 39: 1137\u20131149.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"e_1_3_4_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3002345"},{"key":"e_1_3_4_22_2","doi-asserted-by":"crossref","unstructured":"Zhu C He Y Savvides M. Feature selective anchor-free module for single-shot object detection. 2019 pp.840\u2013849.","DOI":"10.1109\/CVPR.2019.00093"},{"key":"e_1_3_4_23_2","doi-asserted-by":"crossref","unstructured":"Redmon J Divvala S Girshick R et al. You only look once: Unified real-time object detection. 2016 pp.779\u2013788.","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_4_24_2","unstructured":"Lyu C et al. Rtmdet: An empirical study of designing real-time object detectors. arXiv preprint arXiv:2212.07784 2022."},{"key":"e_1_3_4_25_2","unstructured":"Bochkovskiy A Wang C-Y Liao H-YM. Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 2020."},{"key":"e_1_3_4_26_2","doi-asserted-by":"crossref","unstructured":"Liu W et al. SSD: single shot multibox detector. 2016 pp.21\u201337. Springer.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_4_27_2","doi-asserted-by":"crossref","unstructured":"Carion N et al. End-to-end object detection with transformers. 2020 pp.213\u2013229. Springer.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_4_28_2","unstructured":"Liu S et al. Dab-detr: dynamic anchor boxes are better queries for detr. arXiv preprint arXiv:2201.12329 2022."},{"key":"e_1_3_4_29_2","doi-asserted-by":"crossref","unstructured":"Meng D et al. Conditional detr for fast training convergence. 2021 pp.3651\u20133660.","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"e_1_3_4_30_2","doi-asserted-by":"crossref","unstructured":"Bucilu\u00c7\u017d C Caruana R Niculescu-Mizil A. Model compression. In: Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining 2006 pp.535\u2013541.","DOI":"10.1145\/1150402.1150464"},{"key":"e_1_3_4_31_2","article-title":"Learning efficient object detection models with knowledge distillation","volume":"30","author":"Chen G","year":"2017","unstructured":"Chen G, Choi W, Yu X, et al. Learning efficient object detection models with knowledge distillation. Adv Neural Inf Process Syst 2017; 30.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_32_2","doi-asserted-by":"crossref","unstructured":"Dai X et al. General instance distillation for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 2021 pp.7842\u20137851.","DOI":"10.1109\/CVPR46437.2021.00775"},{"key":"e_1_3_4_33_2","doi-asserted-by":"crossref","unstructured":"Li Q Jin S Yan J. Mimicking very efficient network for object detection. In: Proceedings of the ieee conference on computer vision and pattern recognition 2017 pp.6356\u20136364.","DOI":"10.1109\/CVPR.2017.776"},{"key":"e_1_3_4_34_2","doi-asserted-by":"crossref","unstructured":"Guo J et al. Distilling object detectors via decoupled features. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 2021 pp.2154\u20132164.","DOI":"10.1109\/CVPR46437.2021.00219"},{"key":"e_1_3_4_35_2","doi-asserted-by":"crossref","unstructured":"Li G et al. Knowledge distillation for object detection via rank mimicking and prediction-guided feature imitation. In: Proceedings of the AAAI conference on artificial intelligence Vol. 36 2022 pp.1306\u20131313.","DOI":"10.1609\/aaai.v36i2.20018"},{"key":"e_1_3_4_36_2","first-page":"5213","article-title":"Distilling object detectors with feature richness","volume":"34","author":"Zhixing D","year":"2021","unstructured":"Zhixing D, et al. Distilling object detectors with feature richness. Adv Neural Inf Process Syst 2021; 34: 5213\u20135224.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_37_2","unstructured":"Yang J Martinez B Bulat A et al. Knowledge distillation via softmax regression representation learning (International Conference on Learning Representations (ICLR) 2021)."},{"key":"e_1_3_4_38_2","doi-asserted-by":"crossref","unstructured":"Yang Z et al. Focal and global knowledge distillation for detectors. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 2022 pp.4643\u20134652.","DOI":"10.1109\/CVPR52688.2022.00460"},{"key":"e_1_3_4_39_2","first-page":"3858","article-title":"Structural knowledge distillation for object detection","volume":"35","author":"De Rijk P","year":"2022","unstructured":"De Rijk P, Schneider L, Cordts M, et al. Structural knowledge distillation for object detection. Adv Neural Inf Process Syst 2022; 35: 3858\u20133870.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_40_2","unstructured":"Chen K et al. Mmdetection: open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 2019."},{"key":"e_1_3_4_41_2","unstructured":"Paszke A et al. Automatic differentiation in pytorch. 2017."},{"key":"e_1_3_4_42_2","doi-asserted-by":"crossref","unstructured":"He K Zhang X Ren S et al. Deep residual learning for image recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 2016 pp.770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_4_43_2","doi-asserted-by":"crossref","unstructured":"Selvaraju RR et al. Grad-Cam: visual explanations from deep networks via gradient-based localization 2017.","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["Intelligent Data Analysis: An International Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1088467X251325364","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/1088467X251325364","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1088467X251325364","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:21:05Z","timestamp":1777454465000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/1088467X251325364"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,19]]},"references-count":42,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["10.1177\/1088467X251325364"],"URL":"https:\/\/doi.org\/10.1177\/1088467x251325364","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"value":"1088-467X","type":"print"},{"value":"1571-4128","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,19]]}}}