{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T15:14:47Z","timestamp":1753888487689,"version":"3.41.2"},"reference-count":42,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T00:00:00Z","timestamp":1699228800000},"content-version":"vor","delay-in-days":309,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62166005"],"award-info":[{"award-number":["62166005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002338","name":"Ministry of Education of the People's Republic of China","doi-asserted-by":"publisher","award":["QJH[2020]245","QJH[2020]248"],"award-info":[{"award-number":["QJH[2020]245","QJH[2020]248"]}],"id":[{"id":"10.13039\/501100002338","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018555","name":"Science and Technology Program of Guizhou Province","doi-asserted-by":"publisher","award":["PTRC[2020]6007-2"],"award-info":[{"award-number":["PTRC[2020]6007-2"]}],"id":[{"id":"10.13039\/501100018555","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2023,1]]},"abstract":"<jats:p>The development of object detection networks has reached a high point, and there have been significant improvements in accuracy and detection speed. Object detection is widely used in intelligent robots, self\u2010driving cars, and other edge\u2010intelligent terminals. Unfortunately, when a detector is allowed to learn new objects in an unfamiliar environment, it can catastrophically forget the objects it has already learned. In particular, reliable and stable knowledge cannot be extracted from old models. Based on this, a new multinetwork mean distillation loss function for open\u2010world domain incremental object detection is presented. To better extract reliable and stable knowledge from old models, we enhanced the distillation output of the detector with a ResNet50 backbone and an output RoI head. The distillation output of the intermediate RPN is softened by adaptive distillation. To obtain more stable results, the ResNet50 backbone and RPN on the channel are zero\u2010averaged. Various incremental steps and stability experiments are performed on two benchmark datasets, PASCAL VOC and MS COCO. The experimental results show the excellent performance of our method in different experimental scenarios, and it is superior to the most advanced methods. For example, in the setting of the batch task, incremental object detection on the PASCAL VOC and MS COCO datasets is improved by 3.4% and 2.1%, respectively.<\/jats:p>","DOI":"10.1155\/2023\/3044155","type":"journal-article","created":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T23:35:13Z","timestamp":1699313713000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A New Multinetwork Mean Distillation Loss Function for Open\u2010World Domain Incremental Object Detection"],"prefix":"10.1155","volume":"2023","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1915-9487","authenticated-orcid":false,"given":"Jing","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9425-7842","authenticated-orcid":false,"given":"Kun","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suhao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinglang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4759-6000","authenticated-orcid":false,"given":"Shaobo","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0194-5888","authenticated-orcid":false,"given":"Xiuhua","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2023,11,6]]},"reference":[{"key":"e_1_2_10_1_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aej.2022.07.039"},{"key":"e_1_2_10_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aej.2020.05.035"},{"key":"e_1_2_10_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aej.2021.03.005"},{"key":"e_1_2_10_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118934"},{"key":"e_1_2_10_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3124133"},{"key":"e_1_2_10_6_2","doi-asserted-by":"crossref","unstructured":"ChenL. YuC. andChenL. A new knowledge distillation for incremental object detection Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN) July 2019 Budapest Hungary IEEE 1\u20137.","DOI":"10.1109\/IJCNN.2019.8851980"},{"key":"e_1_2_10_7_2","doi-asserted-by":"crossref","unstructured":"HaoY. FuY. JiangY. G. andTianQ. An end-to-end architecture for class-incremental object detection with knowledge distillation Proceedings of the 2019 IEEE International Conference on Multimedia and Expo (ICME) July 2019 Shanghai China IEEE 1\u20136.","DOI":"10.1109\/ICME.2019.00009"},{"key":"e_1_2_10_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"e_1_2_10_9_2","doi-asserted-by":"crossref","unstructured":"ShmelkovK. SchmidC. andAlahariK. Incremental Learning of Object Detectors without Catastrophic forgetting Proceedings of the IEEE International Conference on Computer Vision (ICCV) August 2017 Venice Italy IEEE 3400\u20133409.","DOI":"10.1109\/ICCV.2017.368"},{"key":"e_1_2_10_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.09.030"},{"key":"e_1_2_10_11_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_2_10_12_2","doi-asserted-by":"crossref","unstructured":"HaoA. MinY. andChenX. Self-mutual distillation learning for continuous sign language recognition Proceedings of the IEEE\/CVF International Conference on Computer Vision October 2021 Montreal Canada 11303\u201311312.","DOI":"10.1109\/ICCV48922.2021.01111"},{"key":"e_1_2_10_13_2","doi-asserted-by":"crossref","unstructured":"LiK. YuL. WangS. andHengP. A. Towards Cross-Modality Medical Image Segmentation with Online Mutual Knowledge distillation Proceedings of the AAAI Conference on Artificial Intelligence January 2020 New York NY USA 775\u2013783.","DOI":"10.1609\/aaai.v34i01.5421"},{"key":"e_1_2_10_14_2","doi-asserted-by":"crossref","unstructured":"XieP.andDuX. Performance-Aware Mutual Knowledge Distillation for Improving Neural Architecture Search Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2022 New Orleans LA USA 11922\u201311932.","DOI":"10.1109\/CVPR52688.2022.01162"},{"key":"e_1_2_10_15_2","doi-asserted-by":"crossref","unstructured":"SonW. NaJ. ChoiJ. andHwangW. Densely guided knowledge distillation using multiple teacher assistants Proceedings of the IEEE\/CVF International Conference on Computer Vision October 2021 Montreal Canada 9395\u20139404.","DOI":"10.1109\/ICCV48922.2021.00926"},{"key":"e_1_2_10_16_2","doi-asserted-by":"crossref","unstructured":"MirzadehS. I. FarajtabarM. LiA. LevineN. MatsukawaA. andGhasemzadehH. Improved Knowledge Distillation via Teacher assistant Proceedings of the AAAI Conference on Artificial Intelligence January 2020 New York NY USA 5191\u20135198.","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"e_1_2_10_17_2","first-page":"13292","article-title":"Learning student-friendly teacher networks for knowledge distillation","volume":"34","author":"Park D. Y.","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_18_2","doi-asserted-by":"crossref","unstructured":"LeeJ. JeongY. KimS. MinJ. andChoM. Learning to Distill Convolutional Features into Compact Local Descriptors Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision January 2021 Waikoloa HI USA 898\u2013908.","DOI":"10.1109\/WACV48630.2021.00094"},{"key":"e_1_2_10_19_2","doi-asserted-by":"crossref","unstructured":"YueK. DengJ. andZhouF. Matching Guided distillation Proceedings of the European Conference on Computer Vision January 2020 Glasgow UK Springer 312\u2013328.","DOI":"10.1007\/978-3-030-58555-6_19"},{"key":"e_1_2_10_20_2","first-page":"5186","article-title":"Dataset distillation with infinitely wide convolutional networks","volume":"34","author":"Nguyen T.","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_21_2","doi-asserted-by":"crossref","unstructured":"CazenavetteG. WangT. TorralbaA. EfrosA. A. andZhuJ. Y. Dataset distillation by matching training trajectories Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2022 Washington DC USA 4750\u20134759.","DOI":"10.1109\/CVPR52688.2022.01045"},{"key":"e_1_2_10_22_2","doi-asserted-by":"crossref","unstructured":"CazenavetteG. WangT. TorralbaA. EfrosA. A. andZhuJ. Y. W. Synthesizing tileable textures via dataset distillation Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2022 New Orleans LA USA 2278\u20132282.","DOI":"10.1109\/CVPRW56347.2022.00252"},{"key":"e_1_2_10_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2017.2773081"},{"key":"e_1_2_10_24_2","doi-asserted-by":"crossref","unstructured":"ZhaoB. XiaoX. GanG. ZhangB. andXiaS. T. Maintaining discrimination and fairness in class incremental learning Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) June 2020 New Orleans LA USA IEEE 13208\u201313217.","DOI":"10.1109\/CVPR42600.2020.01322"},{"key":"e_1_2_10_25_2","first-page":"30492","article-title":"Bridging non Co-occurrence with unlabeled in-the-wild data for incremental object detection","volume":"34","author":"Dong N.","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_26_2","doi-asserted-by":"crossref","unstructured":"AbdelsalamM. FaramarziM. SodhaniS. andChandarS. Iirc: incremental implicitly-refined classification Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2021 Washington DC USA 11038\u201311047.","DOI":"10.1109\/CVPR46437.2021.01089"},{"key":"e_1_2_10_27_2","doi-asserted-by":"crossref","unstructured":"DongS. HongX. TaoX. ChangX. WeiX. andGongY. Few-shot class-incremental learning via relation knowledge distillation Proceedings of the AAAI Conference on Artificial Intelligence June 2021 Washington DC USA 1255\u20131263.","DOI":"10.1609\/aaai.v35i2.16213"},{"key":"e_1_2_10_28_2","doi-asserted-by":"crossref","unstructured":"CastroF. M. Mar\u00edn-Jim\u00e9nezM. J. GuilN. SchmidC. andAlahariK. End-to-end incremental learning Proceedings of the European Conference on Computer Vision (ECCV) July 2018 Munich Germany Springer 233\u2013248.","DOI":"10.1007\/978-3-030-01258-8_15"},{"key":"e_1_2_10_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2019.2963461"},{"key":"e_1_2_10_30_2","unstructured":"LiD. TasciS. GhoshS. ZhuJ. ZhangJ. andHeckL. R. I. L. O. D. Near real-time incremental learning for object detection at the edge Proceedings of the 4th ACM\/IEEE Symposium on Edge Computing November 2019 Arlington VA USA 113\u2013126."},{"key":"e_1_2_10_31_2","doi-asserted-by":"crossref","unstructured":"WuY. ChenY. WangL. YeY. LiuZ. GuoY. andFuY. Large scale incremental learning Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2019 Washington DC USA 374\u2013382.","DOI":"10.1109\/CVPR.2019.00046"},{"key":"e_1_2_10_32_2","doi-asserted-by":"crossref","unstructured":"HouS. PanX. LoyC. C. WangZ. andLinD. Learning a unified classifier incrementally via rebalancing Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) August 2019 Long Beach CA USA IEEE 831\u2013839.","DOI":"10.1109\/CVPR.2019.00092"},{"key":"e_1_2_10_33_2","doi-asserted-by":"crossref","unstructured":"DouillardA. CordM. OllionC. RobertT. andValleE. Podnet: pooled outputs distillation for small-tasks incremental learning Proceedings of the European Conference on Computer Vision August 2020 Glasgow UK Springer 86\u2013102.","DOI":"10.1007\/978-3-030-58565-5_6"},{"key":"e_1_2_10_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108863"},{"key":"e_1_2_10_35_2","article-title":"Learning to learn by gradient descent by gradient descent","volume":"29","author":"Andrychowicz M.","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_36_2","unstructured":"FinnC. AbbeelP. andLevineS. Model-agnostic meta-learning for fast adaptation of deep networks Proceedings of the International Conference on Machine Learning PMLR August 2017 Sydney Australia 1126\u20131135."},{"key":"e_1_2_10_37_2","unstructured":"FranceschiL. FrasconiP. SalzoS. GrazziR. andPontilM. Bilevel programming for hyperparameter optimization and meta-learning Proceedings of the International Conference on Machine Learning July 2018 Baltimore MD USA PMLR 1568\u20131577."},{"key":"e_1_2_10_38_2","article-title":"Prototypical networks for few-shot learning","volume":"30","author":"Snell J.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_39_2","doi-asserted-by":"crossref","unstructured":"KediaA.andChinthakindiS. C. Keep learning: self-supervised meta-learning for learning from inference Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Maintenant June 2021 Europe UK 63\u201377.","DOI":"10.18653\/v1\/2021.eacl-main.6"},{"key":"e_1_2_10_40_2","article-title":"Meta-gradient reinforcement learning","volume":"31","author":"Xu Z.","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_41_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"e_1_2_10_42_2","doi-asserted-by":"crossref","unstructured":"LinT. Y. MaireM. BelongieS. HaysJ. PeronaP. RamananD. andZitnickC. L. Microsoft coco: common objects in context Proceedings of the European conference on computer vision (ECCV) October 2014 Tel Aviv Israel Springer 740\u2013755.","DOI":"10.1007\/978-3-319-10602-1_48"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijis\/2023\/3044155.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijis\/2023\/3044155.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2023\/3044155","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T05:18:19Z","timestamp":1735622299000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2023\/3044155"}},"subtitle":[],"editor":[{"given":"Gennaro","family":"Vessio","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":42,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["10.1155\/2023\/3044155"],"URL":"https:\/\/doi.org\/10.1155\/2023\/3044155","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"type":"print","value":"0884-8173"},{"type":"electronic","value":"1098-111X"}],"subject":[],"published":{"date-parts":[[2023,1]]},"assertion":[{"value":"2023-04-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-10-11","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-11-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"3044155"}}