{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T04:04:59Z","timestamp":1730174699913,"version":"3.28.0"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726453","type":"print"},{"value":"9783031726460","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72646-0_10","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T08:45:29Z","timestamp":1730105129000},"page":"166-183","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MapDistill: Boosting Efficient Camera-Based HD Map Construction via\u00a0Camera-LiDAR Fusion Model Distillation"],"prefix":"10.1007","author":[{"given":"Xiaoshuai","family":"Hao","sequence":"first","affiliation":[]},{"given":"Ruikai","family":"Li","sequence":"additional","affiliation":[]},{"given":"Hui","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Dingzhe","family":"Li","sequence":"additional","affiliation":[]},{"given":"Rong","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Sangil","family":"Jung","sequence":"additional","affiliation":[]},{"given":"Seung-In","family":"Park","sequence":"additional","affiliation":[]},{"given":"ByungIn","family":"Yoo","sequence":"additional","affiliation":[]},{"given":"Haimei","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Borse, S., et al.: X-align: cross-modal cross-view alignment for bird\u2019s-eye-view segmentation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3287\u20133297 (2023)","DOI":"10.1007\/s00138-023-01400-7"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11618\u201311628 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"10_CR3","unstructured":"Chen, G., Choi, W., Yu, X., Han, T., Chandraker, M.: Learning efficient object detection models with knowledge distillation. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"10_CR4","unstructured":"Chen, S., Cheng, T., Wang, X., Meng, W., Zhang, Q., Liu, W.: Efficient and robust 2D-TO-BEV representation learning via geometry-guided kernel transformer. arXiv preprint arXiv:2206.04584 (2022)"},{"key":"10_CR5","unstructured":"Chen, Z., Li, Z., Zhang, S., Fang, L., Jiang, Q., Zhao, F.: BEVDistill: cross-modal BEV distillation for multi-view 3D object detection. arXiv preprint arXiv:2211.09386 (2022)"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Cho, H., Choi, J., Baek, G., Hwang, W.: itKD: interchange transfer-based knowledge distillation for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13540\u201313549 (2023)","DOI":"10.1109\/CVPR52729.2023.01301"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Ding, W., Qiao, L., Qiu, X., Zhang, C.: PivotNet: vectorized pivot learning for end-to-end HD map construction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3672\u20133682 (2023)","DOI":"10.1109\/ICCV51070.2023.00340"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Gou, J., Yu, B., Maybank, S.J., Tao, D.: Knowledge distillation: a survey. Int. J. Comput. Vis. 129(6), 1789\u20131819 (2021)","DOI":"10.1007\/s11263-021-01453-z"},{"key":"10_CR9","unstructured":"Hao, X., et al.: Is your HD map constructor reliable under sensor corruptions? arXiv preprint arXiv:2406.12214 (2024)"},{"key":"10_CR10","unstructured":"Hao, X., et al.: Team Samsung-RAL: technical report for 2024 RoboDrive challenge-robust map segmentation track. arXiv preprint arXiv:2405.10567 (2024)"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Hao, X., et al.: MBFusion: a new multi-modal BEV feature fusion method for HD map construction. In: IEEE International Conference on Robotics and Automation (2024)","DOI":"10.1109\/ICRA57147.2024.10609873"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"10_CR13","unstructured":"Hendy, N., et al.: FISHING net: future inference of semantic heatmaps in grids. arXiv preprint arXiv:2006.09917 (2020)"},{"key":"10_CR14","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"10_CR15","unstructured":"Huang, P., et al.: TiG-BEV: multi-view BEV 3D object detection via target inner-geometry learning. arXiv preprint arXiv:2212.13979 (2022)"},{"key":"10_CR16","unstructured":"Kong, L., et\u00a0al.: The RoboDrive challenge: drive anytime anywhere in any condition. arXiv preprint arXiv:2405.08816 (2024)"},{"key":"10_CR17","unstructured":"Li, D., et\u00a0al.: What foundation models can bring for robot learning in manipulation: a survey. arXiv preprint arXiv:2404.18201 (2024)"},{"key":"10_CR18","unstructured":"Li, J., Lu, M., Liu, J., Guo, Y., Du, L., Zhang, S.: BEV-LGKD: a unified LiDAR-guided knowledge distillation framework for BEV 3D object detection. arXiv preprint arXiv:2212.00623 (2022)"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Li, Q., Wang, Y., Wang, Y., Zhao, H.: HDMapNet: an online HD map construction and evaluation framework. In: IEEE International Conference on Robotics and Automation, pp. 4628\u20134634 (2022)","DOI":"10.1109\/ICRA46639.2022.9812383"},{"key":"10_CR20","unstructured":"Li, Y., Chen, Y., Qi, X., Li, Z., Sun, J., Jia, J.: Unifying voxel-based representation with transformer for 3D object detection. Adv. Neural Inf. Process. Syst. 35, 18442\u201318455 (2022)"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: BEVFormer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: European Conference on Computer Vision, pp. 1\u201318 (2022)","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"10_CR22","unstructured":"Liang, T., et al.: BEVFusion: a simple and robust lidar-camera fusion framework. Adv. Neural Inf. Process. Syst. 35, 10421\u201310434 (2022)"},{"key":"10_CR23","unstructured":"Liao, B., et al.: MapTR: structured modeling and learning for online vectorized HD map construction. In: International Conference on Learning Representations (2023)"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Liao, B., et al.: MapTRv2: an end-to-end framework for online vectorized HD map construction. arXiv preprint arXiv:2308.05736 (2023)","DOI":"10.1007\/s11263-024-02235-z"},{"key":"10_CR25","unstructured":"Liu, Y., Yuan, T., Wang, Y., Wang, Y., Zhao, H.: VectorMapNet: end-to-end vectorized HD map learning. In: International Conference on Machine Learning, pp. 22352\u201322369 (2023)"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer V2: scaling up capacity and resolution. In: International Conference on Computer Vision and Pattern Recognition, pp. 11999\u201312009 (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9992\u201310002 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: BEVFusion: multi-task multi-sensor fusion with unified bird\u2019s-eye view representation. In: IEEE International Conference on Robotics and Automation, pp. 2774\u20132781 (2023)","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"10_CR29","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019)"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Malkauthekar, M.: Analysis of Euclidean distance and Manhattan distance measure in face recognition. In: Third International Conference on Computational Intelligence and Information Technology (CIIT 2013), pp. 503\u2013507. IET (2013)","DOI":"10.1049\/cp.2013.2636"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Mirzadeh, S.I., Farajtabar, M., Li, A., Levine, N., Matsukawa, A., Ghasemzadeh, H.: Improved knowledge distillation via teacher assistant. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 5191\u20135198 (2020)","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"10_CR32","unstructured":"Mukhoti, J., Kulharia, V., Sanyal, A., Golodetz, S., Torr, P., Dokania, P.: Calibrating deep neural networks using focal loss. Adv. Neural Inf. Process. Syst. 33, 15288\u201315299 (2020)"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Philion, J., Fidler, S.: Lift, splat, shoot: encoding images from arbitrary camera rigs by implicitly unprojecting to 3D. In: European Conference on Computer Vision, pp. 194\u2013210 (2020)","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Qiao, L., Ding, W., Qiu, X., Zhang, C.: End-to-end vectorized HD-map construction with piecewise Bezier curve. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13218\u201313228 (2023)","DOI":"10.1109\/CVPR52729.2023.01270"},{"key":"10_CR35","doi-asserted-by":"crossref","unstructured":"Salazar-Gomez, G., et al.: TransFuseGrid: transformer-based lidar-RGB fusion for semantic grid prediction. In: International Conference on Control, Automation, Robotics and Vision, pp. 268\u2013273 (2022)","DOI":"10.1109\/ICARCV57592.2022.10004276"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Shang, C., Li, H., Meng, F., Wu, Q., Qiu, H., Wang, L.: Incrementer: transformer for class-incremental semantic segmentation with knowledge distillation focusing on old class. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7214\u20137224 (2023)","DOI":"10.1109\/CVPR52729.2023.00697"},{"key":"10_CR37","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International conference on machine learning, pp. 6105\u20136114 (2019)"},{"key":"10_CR38","doi-asserted-by":"crossref","unstructured":"Tang, K., et\u00a0al.: THMA: tencent HD map AI system for creating HD map annotations. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 15585\u201315593 (2023)","DOI":"10.1609\/aaai.v37i13.26848"},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Wang, S., Li, W., Liu, W., Liu, X., Zhu, J.: LiDAR2Map: in defense of lidar-based semantic map construction using online camera distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5186\u20135195 (2023)","DOI":"10.1109\/CVPR52729.2023.00502"},{"key":"10_CR40","doi-asserted-by":"crossref","unstructured":"Wang, W., et\u00a0al.: InternImage: exploring large-scale vision foundation models with deformable convolutions. arXiv preprint arXiv:2211.05778 (2022)","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"Wang, Z., Li, D., Luo, C., Xie, C., Yang, X.: DistillBEV: boosting multi-camera 3D object detection with cross-modal knowledge distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8637\u20138646 (2023)","DOI":"10.1109\/ICCV51070.2023.00793"},{"key":"10_CR42","doi-asserted-by":"crossref","unstructured":"Xiong, X., Liu, Y., Yuan, T., Wang, Y., Wang, Y., Zhao, H.: Neural map prior for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17535\u201317544 (2023)","DOI":"10.1109\/CVPR52729.2023.01682"},{"key":"10_CR43","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1007\/978-3-031-19815-1_39","volume-title":"Computer Vision \u2013 ECCV 2022","author":"X Yan","year":"2022","unstructured":"Yan, X., et al.: 2DPASS: 2D priors assisted semantic segmentation on\u00a0LiDAR point clouds. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, pp. 677\u2013695. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_39"},{"issue":"10","key":"10_CR44","doi-asserted-by":"publisher","first-page":"3337","DOI":"10.3390\/s18103337","volume":"18","author":"Y Yan","year":"2018","unstructured":"Yan, Y., Mao, Y., Li, B.: SECOND: sparsely embedded convolutional detection. Sensors 18(10), 3337 (2018)","journal-title":"Sensors"},{"key":"10_CR45","doi-asserted-by":"crossref","unstructured":"Yang, C., et\u00a0al.: BEVFormer v2: adapting modern image backbones to bird\u2019s-eye-view recognition via perspective supervision. arXiv preprint arXiv:2211.10439 (2022)","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"10_CR46","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: Label-guided knowledge distillation for continual semantic segmentation on 2D images and 3D point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18601\u201318612 (2023)","DOI":"10.1109\/ICCV51070.2023.01705"},{"key":"10_CR47","unstructured":"Zhang, G., et al.: Online map vectorization for autonomous driving: a rasterization perspective. arXiv preprint arXiv:2306.10502 (2023)"},{"key":"10_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: DTFD-MIL: double-tier feature distillation multiple instance learning for histopathology whole slide image classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18802\u201318812 (2022)","DOI":"10.1109\/CVPR52688.2022.01824"},{"issue":"4","key":"10_CR49","first-page":"5099","volume":"45","author":"Q Zhang","year":"2022","unstructured":"Zhang, Q., Cheng, X., Chen, Y., Rao, Z.: Quantifying the knowledge in a DNN to explain knowledge distillation for classification. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 5099\u20135113 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR50","unstructured":"Zhang, Y., et al.: BEVerse: unified perception and prediction in birds-eye-view for vision-centric autonomous driving. arXiv preprint arXiv:2205.09743 (2022)"},{"key":"10_CR51","doi-asserted-by":"crossref","unstructured":"Zhao, H., Zhang, Q., Zhao, S., Chen, Z., Zhang, J., Tao, D.: SimDistill: simulated multi-modal distillation for BEV 3D object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 7460\u20137468 (2024)","DOI":"10.1609\/aaai.v38i7.28577"},{"issue":"8","key":"10_CR52","doi-asserted-by":"publisher","first-page":"10070","DOI":"10.1109\/TPAMI.2023.3248583","volume":"45","author":"Z Zheng","year":"2023","unstructured":"Zheng, Z., et al.: Localization distillation for object detection. IEEE Trans. Pattern Anal. Mach. Intell. 45(8), 10070\u201310083 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR53","doi-asserted-by":"crossref","unstructured":"Zhou, S., Liu, W., Hu, C., Zhou, S., Ma, C.: UniDistill: a universal cross-modality knowledge distillation framework for 3d object detection in bird\u2019s-eye view. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5116\u20135125 (2023)","DOI":"10.1109\/CVPR52729.2023.00495"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72646-0_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T08:50:23Z","timestamp":1730105423000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72646-0_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"ISBN":["9783031726453","9783031726460"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72646-0_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"28 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}