{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T14:40:31Z","timestamp":1777560031928,"version":"3.51.4"},"reference-count":29,"publisher":"SAGE Publications","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AIC"],"published-print":{"date-parts":[[2023,10,13]]},"abstract":"<jats:p>It is a generic paradigm to treat all samples equally in 3D object detection. Although some works focus on discriminating samples in the training process of object detectors, the issue of whether a sample detects its target GT (Ground Truth) during training process has never been studied. In this work, we first point out that discriminating the samples that detect their target GT and the samples that don\u2019t detect their target GT is beneficial to improve the performance measured in terms of mAP (mean Average Precision). Then we propose a novel approach name as DW (Detected Weight). The proposed approach dynamically calculates and assigns different weights to detected and undetected samples, which suppresses the former and promotes the latter. The approach is simple, low-calculation and can be integrated with available weight approaches. Further, it can be applied to almost 3D detectors, even 2D detectors because it is nothing to do with network structures. We evaluate the proposed approach with six state-of-the-art 3D detectors on two datasets. The experiment results show that the proposed approach improves mAP significantly.<\/jats:p>","DOI":"10.3233\/aic-230008","type":"journal-article","created":{"date-parts":[[2023,10,6]],"date-time":"2023-10-06T10:35:04Z","timestamp":1696588504000},"page":"285-295","source":"Crossref","is-referenced-by-count":0,"title":["DW: Detected weight for 3D object detection"],"prefix":"10.1177","volume":"36","author":[{"given":"Zhi","family":"Huang","sequence":"first","affiliation":[{"name":"School of Information Engineering, Key Laboratory of IOT Security at Mianyang Teachers\u2019 College of Sichuan Province, Mianyang Teachers\u2019 College, Sichuan Province, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/AIC-230008_ref2","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Cao, K.\u00a0Chen, C.C.\u00a0Loy and D.\u00a0Lin, Prime sample attention in object detection, in: CVPR, 2020, pp.\u00a011580\u201311588.","DOI":"10.1109\/CVPR42600.2020.01160"},{"key":"10.3233\/AIC-230008_ref3","doi-asserted-by":"crossref","unstructured":"X.\u00a0Cheng, S.\u00a0Qiu, Z.\u00a0Zou, J.\u00a0Pu and X.\u00a0Xue, Understanding depth map progressively: Adaptive distance interval separation for monocular 3d object detection, in: IJCNN, 2023.","DOI":"10.1109\/IJCNN54540.2023.10191066"},{"key":"10.3233\/AIC-230008_ref4","doi-asserted-by":"publisher","first-page":"64608","DOI":"10.1109\/ACCESS.2023.3288112","article-title":"Multi-camera 3D object detection for autonomous driving using deep learning and self-attention mechanism","volume":"11","author":"Hazarika","year":"2023","journal-title":"IEEE Access"},{"key":"10.3233\/AIC-230008_ref5","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Huang, Y.\u00a0Wang, X.\u00a0Tang and H.\u00a0Sun, Boundary-aware set abstraction for 3D object detection, in: IJCNN, 2023.","DOI":"10.1109\/IJCNN54540.2023.10191728"},{"issue":"4","key":"10.3233\/AIC-230008_ref6","doi-asserted-by":"publisher","first-page":"5973","DOI":"10.1007\/s11042-021-11801-3","article-title":"Monocular 3D object detection via estimation of paired keypoints for autonomous driving","volume":"81","author":"Ji","year":"2022","journal-title":"Multim. Tools Appl."},{"key":"10.3233\/AIC-230008_ref7","doi-asserted-by":"publisher","first-page":"2749","DOI":"10.1109\/TIP.2023.3274479","article-title":"Stereoscopic vision recalling memory for monocular 3D object detection","volume":"32","author":"Kim","year":"2023","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.3233\/AIC-230008_ref8","doi-asserted-by":"crossref","unstructured":"A.H.\u00a0Lang, S.\u00a0Vora, H.\u00a0Caesar, L.\u00a0Zhou, J.\u00a0Yang and O.\u00a0Beijbom, PointPillars: Fast encoders for object detection from point clouds, in: CVPR, 2019, pp.\u00a012697\u201312705.","DOI":"10.1109\/CVPR.2019.01298"},{"key":"10.3233\/AIC-230008_ref9","doi-asserted-by":"crossref","unstructured":"B.\u00a0Li, Y.\u00a0Liu and X.\u00a0Wang, Gradient harmonized single-stage detector, in: AAAI, 2019, pp.\u00a08577\u20138584.","DOI":"10.1609\/aaai.v33i01.33018577"},{"issue":"7","key":"10.3233\/AIC-230008_ref10","first-page":"8284","article-title":"Detection-friendly dehazing: Object detection in real-world hazy scenes","volume":"45","author":"Li","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"issue":"8","key":"10.3233\/AIC-230008_ref11","doi-asserted-by":"publisher","first-page":"4855","DOI":"10.1109\/LRA.2023.3290526","article-title":"Geo-localization with transformer-based 2D-3D match network","volume":"8","author":"Li","year":"2023","journal-title":"IEEE Robotics and Automation Letters"},{"issue":"2","key":"10.3233\/AIC-230008_ref12","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","article-title":"Focal loss for dense object detection","volume":"42","author":"Lin","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"10","key":"10.3233\/AIC-230008_ref13","doi-asserted-by":"publisher","first-page":"3388","DOI":"10.1109\/TPAMI.2020.2981890","article-title":"Imbalance problems in object detection: A reviewk","volume":"43","author":"Oksuz","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.3233\/AIC-230008_ref14","unstructured":"C.R.\u00a0Qi, X.\u00a0Chen, O.\u00a0Litany and L.J.\u00a0Guibas, ImVoteNet: Boosting 3D object detection in point clouds with image votes, in: CVPR, 2020, pp.\u00a04403\u20134412."},{"key":"10.3233\/AIC-230008_ref15","doi-asserted-by":"crossref","unstructured":"C.R.\u00a0Qi, O.\u00a0Litany, K.\u00a0He and L.J.\u00a0Guibas, Deep hough voting for 3D object detection in point clouds, in: ICCV, 2019, pp.\u00a09276\u20139285.","DOI":"10.1109\/ICCV.2019.00937"},{"key":"10.3233\/AIC-230008_ref16","doi-asserted-by":"crossref","unstructured":"C.R.\u00a0Qi, H.\u00a0Su, K.\u00a0Mo and L.J.\u00a0Guibas, PointNet: Deep learning on point sets for 3D classification and segmentation, in: CVPR, 2017, pp.\u00a077\u201385.","DOI":"10.1109\/CVPR.2017.16"},{"key":"10.3233\/AIC-230008_ref17","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1109\/OJITS.2023.3283768","article-title":"3-D vehicle detection enhancement using tracking feedback in sparse point clouds environments","volume":"4","author":"Qian","year":"2023","journal-title":"IEEE Open Journal of Intelligent Transportation Systems"},{"key":"10.3233\/AIC-230008_ref18","doi-asserted-by":"crossref","unstructured":"J.\u00a0Redmon, S.K.\u00a0Divvala, R.B.\u00a0Girshick and A.\u00a0Farhadi, You only look once: Unified, real-time object detection, in: CVPR, 2016, pp.\u00a0779\u2013788.","DOI":"10.1109\/CVPR.2016.91"},{"key":"10.3233\/AIC-230008_ref19","doi-asserted-by":"crossref","unstructured":"D.\u00a0Rukhovich, A.\u00a0Vorontsova and A.\u00a0Konushin, ImVoxelNet: Image to voxels projection for monocular and multi-view general-purpose 3D object detection, in: WACV, 2022, pp.\u00a01265\u20131274.","DOI":"10.1109\/WACV51458.2022.00133"},{"issue":"6","key":"10.3233\/AIC-230008_ref20","doi-asserted-by":"publisher","first-page":"5971","DOI":"10.1109\/TITS.2023.3259582","article-title":"Real-time point cloud object detection via voxel-point geometry abstraction","volume":"24","author":"Shi","year":"2023","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"8","key":"10.3233\/AIC-230008_ref21","first-page":"2647","article-title":"From points to parts: 3D object detection from point cloud with part-aware and part-aggregation network","volume":"43","author":"Shi","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.3233\/AIC-230008_ref22","doi-asserted-by":"crossref","unstructured":"V.A.\u00a0Sindagi, Y.\u00a0Zhou and O.\u00a0Tuzel, MVX-Net: Multimodal VoxelNet for 3D object detection, in: ICRA, 2019, pp.\u00a07276\u20137282.","DOI":"10.1109\/ICRA.2019.8794195"},{"key":"10.3233\/AIC-230008_ref23","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Song, H.\u00a0Wei, C.\u00a0Jia, Y.\u00a0Xia, X.\u00a0Li and C.\u00a0Zhang, VP-Net: Voxels as points for 3-D object detection, IEEE Transactions on Geoscience and Remote Sensing 61 (2023), 00.","DOI":"10.1109\/TGRS.2023.3271020"},{"key":"10.3233\/AIC-230008_ref24","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Xiang, W.\u00a0Kim, W.\u00a0Chen, J.\u00a0Ji, C.B.\u00a0Choy, H.\u00a0Su, L.J.\u00a0Guibas and S.\u00a0Savarese, ObjectNet3D: A large scale database for 3D object recognition, in: ECCV, 2016, pp.\u00a0160\u2013176.","DOI":"10.1007\/978-3-319-46484-8_10"},{"key":"10.3233\/AIC-230008_ref25","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Yan, Y.\u00a0Mao and B.\u00a0Li, Second: Sparsely embedded convolutional detection, Sensors 18(10) (2018).","DOI":"10.3390\/s18103337"},{"issue":"4","key":"10.3233\/AIC-230008_ref26","doi-asserted-by":"publisher","first-page":"2068","DOI":"10.1109\/TCSVT.2021.3082763","article-title":"Temporal-channel transformer for 3D lidar-based video object detection for autonomous driving","volume":"32","author":"Yuan","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.3233\/AIC-230008_ref27","doi-asserted-by":"publisher","first-page":"72803","DOI":"10.1109\/ACCESS.2023.3292174","article-title":"Infrastructure 3D target detection based on multi-mode fusion for intelligent and connected vehicles","volume":"11","author":"Zhang","year":"2023","journal-title":"IEEE Access"},{"issue":"12","key":"10.3233\/AIC-230008_ref28","doi-asserted-by":"publisher","first-page":"4735","DOI":"10.1109\/TCSVT.2021.3102025","article-title":"Transformer3D-Det: Improving 3D object detection by vote refinement","volume":"31","author":"Zhao","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.3233\/AIC-230008_ref29","doi-asserted-by":"publisher","first-page":"798","DOI":"10.1109\/LSP.2023.3283468","article-title":"DTSSD: Dual-channel transformer-based network for point-based 3D object detection","volume":"30","author":"Zheng","year":"2023","journal-title":"IEEE Signal Processing Letters"},{"key":"10.3233\/AIC-230008_ref30","unstructured":"Y.\u00a0Zhou, P.\u00a0Sun, Y.\u00a0Zhang, D.\u00a0Anguelov, J.\u00a0Gao, T.\u00a0Ouyang, J.\u00a0Guo, J.\u00a0Ngiam and V.\u00a0Vasudevan, End-to-end multi-view fusion for 3D object detection in LiDAR point clouds, in: CoRL, 2019, pp.\u00a0923\u2013932."}],"container-title":["AI Communications"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/AIC-230008","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T18:28:10Z","timestamp":1777400890000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/AIC-230008"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,13]]},"references-count":29,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.3233\/aic-230008","relation":{},"ISSN":["1875-8452","0921-7126"],"issn-type":[{"value":"1875-8452","type":"electronic"},{"value":"0921-7126","type":"print"}],"subject":[],"published":{"date-parts":[[2023,10,13]]}}}