{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T04:23:48Z","timestamp":1741753428518,"version":"3.38.0"},"reference-count":54,"publisher":"SAGE Publications","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AIC"],"published-print":{"date-parts":[[2024,9,18]]},"abstract":"<jats:p>Traditional object detection algorithms operate within a closed set, where the training data may not cover all real-world objects. Therefore, the issue of open-world object detection has attracted significant attention. Open-world object detection faces two major challenges: \u201cneglecting unknown objects\u201d and \u201cmisclassifying unknown objects as known ones.\u201d In our study, we address these challenges by utilizing the Region Proposal Network (RPN) outputs to identify potential unknown objects with high object scores that do not overlap with ground truth annotations. We introduce the reselection mechanism, which separates unknown objects from the background. Subsequently, we employ the simulated annealing algorithm to disentangle features of unknown and known classes, guiding the detector\u2019s learning process. Our method has improved on multiple evaluation metrics such as U-mAP, U-recall, and UDP, greatly alleviating the challenges faced by open world object detection.<\/jats:p>","DOI":"10.3233\/aic-230270","type":"journal-article","created":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T17:56:13Z","timestamp":1714154173000},"page":"637-653","source":"Crossref","is-referenced-by-count":0,"title":["Open-world object detection: A solution based on reselection mechanism and feature disentanglement"],"prefix":"10.1177","volume":"37","author":[{"given":"Tian","family":"Lin","sequence":"first","affiliation":[{"name":"Changchun University of Science and Technology, Academy of computer science and technology, Changchun, China"}]},{"given":"Li","family":"Hua","sequence":"additional","affiliation":[{"name":"Changchun University of Science and Technology, Academy of computer science and technology, Changchun, China"}]},{"given":"Li","family":"Linxuan","sequence":"additional","affiliation":[{"name":"Changchun University of Science and Technology, Academy of computer science and technology, Changchun, China"}]},{"given":"Bai","family":"Chuanao","sequence":"additional","affiliation":[{"name":"Changchun University of Science and Technology, Academy of computer science and technology, Changchun, China"}]}],"member":"179","reference":[{"key":"10.3233\/AIC-230270_ref1","doi-asserted-by":"crossref","unstructured":"R.\u00a0Aljundi, F.\u00a0Babiloni, M.\u00a0Elhoseiny et al., Memory aware synapses: Learning what (not) to forget, in: Proceedings of the European Conference on Computer Vision (ECCV), 2018, 139\u2013154.","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"10.3233\/AIC-230270_ref2","doi-asserted-by":"crossref","unstructured":"A.\u00a0Bendale and T.\u00a0Boult, Towards open world recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp.\u00a01893\u20131902.","DOI":"10.1109\/CVPR.2015.7298799"},{"key":"10.3233\/AIC-230270_ref3","doi-asserted-by":"crossref","unstructured":"N.\u00a0Carion, F.\u00a0Massa, G.\u00a0Synnaeve et al., End-to-end object detection with transformers, in: Computer Vision\u00a0\u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I 16, Springer International Publishing, 2020, pp.\u00a0213\u2013229.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"10.3233\/AIC-230270_ref4","doi-asserted-by":"crossref","unstructured":"F.M.\u00a0Castro, M.J.\u00a0Mar\u00edn-Jim\u00e9nez, N.\u00a0Guil et al., End-to-end incremental learning, in: Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp.\u00a0233\u2013248.","DOI":"10.1007\/978-3-030-01258-8_15"},{"key":"10.3233\/AIC-230270_ref5","doi-asserted-by":"crossref","unstructured":"A.\u00a0Dhamija, M.\u00a0Gunther, J.\u00a0Ventura et al., The overlooked elephant of object detection: Open set, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2020, pp.\u00a01021\u20131030.","DOI":"10.1109\/WACV45572.2020.9093355"},{"key":"10.3233\/AIC-230270_ref6","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The Pascal visual object classes (voc) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"International journal of computer vision"},{"issue":"4","key":"10.3233\/AIC-230270_ref7","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/S1364-6613(99)01294-2","article-title":"Catastrophic forgetting in connectionist networks","volume":"3","author":"French","year":"1999","journal-title":"Trends in cognitive sciences"},{"issue":"03","key":"10.3233\/AIC-230270_ref8","doi-asserted-by":"publisher","first-page":"191","DOI":"10.16451\/j.cnki.issn1003-6059.202303001","article-title":"Challenges in autonomous driving safety: Behavior decision and motion planning","volume":"36","author":"Guan","year":"2023","journal-title":"Pattern Recognition and Artificial Intelligence"},{"key":"10.3233\/AIC-230270_ref9","doi-asserted-by":"crossref","unstructured":"A.\u00a0Gupta, S.\u00a0Narayan, K.J.\u00a0Joseph et al., Ow-detr: Open-world detection transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp.\u00a09235\u20139244.","DOI":"10.1109\/CVPR52688.2022.00902"},{"key":"10.3233\/AIC-230270_ref10","doi-asserted-by":"crossref","unstructured":"J.\u00a0Han, Y.\u00a0Ren, J.\u00a0Ding et al., Expanding low-density latent regions for open-set object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp.\u00a09591\u20139600.","DOI":"10.1109\/CVPR52688.2022.00937"},{"issue":"1","key":"10.3233\/AIC-230270_ref11","first-page":"100","article-title":"Algorithm AS 136: A k-means clustering algorithm","volume":"28","author":"Hartigan","year":"1979","journal-title":"Journal of the royal statistical society. series c (applied statistics)"},{"key":"10.3233\/AIC-230270_ref12","doi-asserted-by":"crossref","unstructured":"K.\u00a0He, X.\u00a0Zhang, S.\u00a0Ren et al., Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp.\u00a0770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.3233\/AIC-230270_ref13","first-page":"14374","article-title":"Meta-consolidation for continual learning","volume":"33","author":"J.","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.3233\/AIC-230270_ref14","doi-asserted-by":"crossref","unstructured":"L.P.\u00a0Jain, W.J.\u00a0Scheirer and T.E.\u00a0Boult, Multi-class open set recognition using probability of inclusion, in: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part III 13, Springer International Publishing, 2014, pp.\u00a0393\u2013409.","DOI":"10.1007\/978-3-319-10578-9_26"},{"key":"10.3233\/AIC-230270_ref15","doi-asserted-by":"crossref","unstructured":"K.J.\u00a0Joseph, S.\u00a0Khan, F.S.\u00a0Khan et al., Towards open world object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp.\u00a05830\u20135840.","DOI":"10.1109\/CVPR46437.2021.00577"},{"key":"10.3233\/AIC-230270_ref16","doi-asserted-by":"crossref","unstructured":"J.\u00a0Kirkpatrick, R.\u00a0Pascanu, N.\u00a0Rabinowitz et al., Overcoming catastrophic forgetting in neural networks, in: Proceedings of the National Academy of Sciences, Vol.\u00a0114, 2017, pp.\u00a03521\u20133526.","DOI":"10.1073\/pnas.1611835114"},{"issue":"4598","key":"10.3233\/AIC-230270_ref17","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1126\/science.220.4598.671","article-title":"Optimization by simulated annealing","volume":"220","author":"Kirkpatrick","year":"1983","journal-title":"science"},{"key":"10.3233\/AIC-230270_ref18","doi-asserted-by":"crossref","unstructured":"Y.\u00a0LeCun, S.\u00a0Chopra, R.\u00a0Hadsell et al., A tutorial on energy-based learning, Predicting structured data 1(0) (2006).","DOI":"10.7551\/mitpress\/7443.003.0014"},{"key":"10.3233\/AIC-230270_ref20","doi-asserted-by":"crossref","unstructured":"T.Y.\u00a0Lin, P.\u00a0Goyal, R.\u00a0Girshick et al., Focal loss for dense object detection, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"10.3233\/AIC-230270_ref21","doi-asserted-by":"crossref","unstructured":"T.Y.\u00a0Lin, M.\u00a0Maire, S.\u00a0Belongie et al., Microsoft coco: Common objects in context, in: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part V 13, Springer International Publishing, 2014, pp.\u00a0740\u2013755.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"10.3233\/AIC-230270_ref23","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Liu, W.\u00a0Zhang and J.\u00a0Wang, Zero-shot adversarial quantization, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp.\u00a01512\u20131521.","DOI":"10.1109\/CVPR46437.2021.00156"},{"key":"10.3233\/AIC-230270_ref24","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Liu, Z.\u00a0Miao, X.\u00a0Zhan et al., Large-scale long-tailed recognition in an open world, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp.\u00a02537\u20132546.","DOI":"10.1109\/CVPR.2019.00264"},{"key":"10.3233\/AIC-230270_ref25","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Ma, H.\u00a0Li, Z.\u00a0Zhang et al., Annealing-based label-transfer learning for open world object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp.\u00a011454\u201311463.","DOI":"10.1109\/CVPR52729.2023.01102"},{"key":"10.3233\/AIC-230270_ref26","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Ma, W.\u00a0Liu, S.\u00a0Bai et al., in: Few-Shot Visual Learning with Contextual Memory and Fine-Grained Calibration[C]\/\/IJCAI, 2020, pp.\u00a0811\u2013817.","DOI":"10.24963\/ijcai.2020\/113"},{"key":"10.3233\/AIC-230270_ref27","doi-asserted-by":"crossref","unstructured":"A.\u00a0Mallya and L.S.\u00a0Packnet, Adding multiple tasks to a single network by iterative pruning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp.\u00a07765\u20137773.","DOI":"10.1109\/CVPR.2018.00810"},{"key":"10.3233\/AIC-230270_ref28","doi-asserted-by":"crossref","unstructured":"M.\u00a0Mancini, M.F.\u00a0Naeem, Y.\u00a0Xian et al., Open world compositional zero-shot learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp.\u00a05222\u20135230.","DOI":"10.1109\/CVPR46437.2021.00518"},{"key":"10.3233\/AIC-230270_ref29","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/S0079-7421(08)60536-8","article-title":"Catastrophic interference in connectionist networks: The sequential learning problem","volume":"24","author":"McCloskey","year":"1989","journal-title":"Psychology of learning and motivation. Academic Press"},{"key":"10.3233\/AIC-230270_ref30","doi-asserted-by":"crossref","unstructured":"D.\u00a0Miller, L.\u00a0Nicholson, F.\u00a0Dayoub et al., Dropout sampling for robust object detection in open-set conditions, in: 2018 IEEE International Conference on Robotics and Automation (ICRA), IEEE, 2018, pp.\u00a03243\u20133249.","DOI":"10.1109\/ICRA.2018.8460700"},{"key":"10.3233\/AIC-230270_ref31","unstructured":"S.\u00a0Pidhorskyi, R.\u00a0Almohsen and G.\u00a0Doretto, Generative probabilistic novelty detection with adversarial autoencoders, Advances in neural information processing systems (2018), 31."},{"key":"10.3233\/AIC-230270_ref32","doi-asserted-by":"crossref","unstructured":"J.\u00a0Rajasegaran, S.\u00a0Khan, M.\u00a0Hayat et al., Itaml: An incremental task-agnostic meta-learning approach, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp.\u00a013588\u201313597.","DOI":"10.1109\/CVPR42600.2020.01360"},{"key":"10.3233\/AIC-230270_ref33","doi-asserted-by":"crossref","unstructured":"S.S.\u00a0Rambhatla, R.\u00a0Chellappa and A.\u00a0Shrivastava, The pursuit of knowledge: Discovering and localizing novel categories using dual memory, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp.\u00a09153\u20139163.","DOI":"10.1109\/ICCV48922.2021.00902"},{"key":"10.3233\/AIC-230270_ref34","doi-asserted-by":"crossref","unstructured":"S.A.\u00a0Rebuffi, A.\u00a0Kolesnikov, G.\u00a0Sperl et al., icarl: Incremental classifier and representation learning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp.\u00a02001\u20132010.","DOI":"10.1109\/CVPR.2017.587"},{"key":"10.3233\/AIC-230270_ref35","doi-asserted-by":"crossref","unstructured":"J.\u00a0Redmon, S.\u00a0Divvala, R.\u00a0Girshick et al., You only look once: Unified, real-time object detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp.\u00a0779\u2013788.","DOI":"10.1109\/CVPR.2016.91"},{"issue":"04","key":"10.3233\/AIC-230270_ref36","doi-asserted-by":"publisher","first-page":"865","DOI":"10.13195\/j.kzyjc.2022.0618","article-title":"A review of 3D object detection research in autonomous driving","volume":"38","author":"Ren","year":"2023","journal-title":"Control and Decision"},{"key":"10.3233\/AIC-230270_ref37","unstructured":"S.\u00a0Ren, K.\u00a0He, R.\u00a0Girshick et al., Faster r-cnn: Towards real-time object detection with region proposal networks, Advances in neural information processing systems 28 (2015)."},{"issue":"7","key":"10.3233\/AIC-230270_ref38","doi-asserted-by":"publisher","first-page":"1757","DOI":"10.1109\/TPAMI.2012.256","article-title":"Toward open set recognition","volume":"35","author":"Scheirer","year":"2012","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"issue":"11","key":"10.3233\/AIC-230270_ref39","doi-asserted-by":"publisher","first-page":"2317","DOI":"10.1109\/TPAMI.2014.2321392","article-title":"Probability models for open set recognition","volume":"36","author":"Scheirer","year":"2014","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"issue":"2","key":"10.3233\/AIC-230270_ref40","doi-asserted-by":"publisher","first-page":"632","DOI":"10.1109\/TAES.2015.150027","article-title":"Open set recognition for automatic target classification with rejection","volume":"52","author":"Scherreik","year":"2016","journal-title":"IEEE Transactions on Aerospace and Electronic Systems"},{"issue":"3","key":"10.3233\/AIC-230270_ref41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3068335","article-title":"DBSCAN revisited, revisited: Why and how you should (still) use DBSCAN","volume":"42","author":"Schubert","year":"2017","journal-title":"ACM Transactions on Database Systems (TODS)"},{"key":"10.3233\/AIC-230270_ref42","unstructured":"J.\u00a0Serra, D.\u00a0Suris, M.\u00a0Miron et al., Overcoming catastrophic forgetting with hard attention to the task, in: International Conference on Machine Learning, PMLR, 2018, pp.\u00a04548\u20134557."},{"key":"10.3233\/AIC-230270_ref43","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","article-title":"Selective search for object recognition","volume":"104","author":"Uijlings","year":"2013","journal-title":"International journal of computer vision"},{"key":"10.3233\/AIC-230270_ref44","doi-asserted-by":"crossref","unstructured":"R.\u00a0Vareto, S.\u00a0Silva, F.\u00a0Costa et al., Towards open-set face recognition using hashing functions, in: 2017 IEEE International Joint Conference on Biometrics (IJCB), IEEE, 2017, pp.\u00a0634\u2013641.","DOI":"10.1109\/BTAS.2017.8272751"},{"key":"10.3233\/AIC-230270_ref45","doi-asserted-by":"crossref","unstructured":"C.Y.\u00a0Wang, A.\u00a0Bochkovskiy and H.Y.M.\u00a0Liao, YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp.\u00a07464\u20137475.","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"10.3233\/AIC-230270_ref46","doi-asserted-by":"crossref","unstructured":"X.\u00a0Wang, R.\u00a0Girdhar, S.X.\u00a0Yu et al., Cut and learn for unsupervised object detection and instance segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp.\u00a03124\u20133134.","DOI":"10.1109\/CVPR52729.2023.00305"},{"issue":"3","key":"10.3233\/AIC-230270_ref48","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3386252","article-title":"Generalizing from a few examples: A survey on few-shot learning","volume":"53","author":"Wang","year":"2020","journal-title":"ACM computing surveys (csur)"},{"key":"10.3233\/AIC-230270_ref49","unstructured":"J.\u00a0Willes, J.\u00a0Harrison, A.\u00a0Harakeh et al., Bayesian embeddings for few-shot open world recognition, in: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022."},{"key":"10.3233\/AIC-230270_ref50","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Wu, Y.\u00a0Lu, X.\u00a0Chen et al., UC-OWOD: Unknown-classified open world object detection, in: Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part X, Cham, Springer Nature Switzerland, 2022, pp.\u00a0193\u2013210.","DOI":"10.1007\/978-3-031-20080-9_12"},{"issue":"5","key":"10.3233\/AIC-230270_ref52","first-page":"7","article-title":"A review of simulated annealing algorithm","volume":"15","author":"Xie","year":"1998","journal-title":"Computer Applications Research"},{"key":"10.3233\/AIC-230270_ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313644"},{"key":"10.3233\/AIC-230270_ref54","doi-asserted-by":"crossref","unstructured":"R.\u00a0Yoshihashi, W.\u00a0Shao, R.\u00a0Kawakami et al., Classification-reconstruction learning for open-set recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp.\u00a04016\u20134025.","DOI":"10.1109\/CVPR.2019.00414"},{"key":"10.3233\/AIC-230270_ref55","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Yue, T.\u00a0Wang, Q.\u00a0Sun et al., Counterfactual zero-shot and open-set visual recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp.\u00a015404\u201315414.","DOI":"10.1109\/CVPR46437.2021.01515"},{"key":"10.3233\/AIC-230270_ref56","doi-asserted-by":"crossref","unstructured":"S.\u00a0Zhang, Z.\u00a0Li, S.\u00a0Yan et al., Distribution alignment: A unified framework for long-tail visual recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp.\u00a02361\u20132370.","DOI":"10.1109\/CVPR46437.2021.00239"},{"key":"10.3233\/AIC-230270_ref58","doi-asserted-by":"crossref","unstructured":"J.\u00a0Zheng, W.\u00a0Li, J.\u00a0Hong et al., Towards open-set object detection and discovery, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp.\u00a03961\u20133970.","DOI":"10.1109\/CVPRW56347.2022.00441"},{"key":"10.3233\/AIC-230270_ref60","doi-asserted-by":"crossref","unstructured":"O.\u00a0Zohar, K.C.\u00a0Wang and S.\u00a0Yeung, Prob: Probabilistic objectness for open world object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp.\u00a011444\u201311453.","DOI":"10.1109\/CVPR52729.2023.01101"}],"container-title":["AI Communications"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/AIC-230270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T07:17:00Z","timestamp":1741677420000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.medra.org\/servlet\/aliasResolver?alias=iospress&doi=10.3233\/AIC-230270"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,18]]},"references-count":54,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.3233\/aic-230270","relation":{},"ISSN":["1875-8452","0921-7126"],"issn-type":[{"type":"electronic","value":"1875-8452"},{"type":"print","value":"0921-7126"}],"subject":[],"published":{"date-parts":[[2024,9,18]]}}}