CLF3D: A Coarse-Labeling Framework to Facilitate 3D Object Detection in Point Clouds
Tremendous scenarios have to be considered for autonomous driving, leading to extremely large amount of point cloud data which need to be labeled for model training. Manually labeling such data is labor-intensive and highly expensive. In this paper, we propose CLF3D, a simple and effective coarse-la...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11039621/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849426004577091584 |
|---|---|
| author | Nuo Cheng Chuanyu Luo Han Li Sikun Ma Shengguang Lei Pu Li |
| author_facet | Nuo Cheng Chuanyu Luo Han Li Sikun Ma Shengguang Lei Pu Li |
| author_sort | Nuo Cheng |
| collection | DOAJ |
| description | Tremendous scenarios have to be considered for autonomous driving, leading to extremely large amount of point cloud data which need to be labeled for model training. Manually labeling such data is labor-intensive and highly expensive. In this paper, we propose CLF3D, a simple and effective coarse-labeling framework designed to improve existing automated labeling methods by fully leveraging scene-specific information in the unlabeled data to significantly enhance detection accuracy. Specifically, CLF3D first utilizes a pre-trained model to generate initial pseudo-labels, which are subsequently refined using a two-stage filtering strategy in combination with an instance bank built from high-quality annotated instances. These refined pseudo-labels are then used to fine-tune the model, progressively improving its detection performance on unlabeled data. Through iterative refinement of pseudo-labels, the model parameters, and the instance bank, CLF3D continuously improves label quality and accuracy. Experimental results demonstrate that the proposed method improves the detection accuracy by up to 14% compared to the originally pre-trained model across datasets of various sizes. This means our approach can reduce 14% of the manual workload for labeling point cloud data in comparison to the existing methods. |
| format | Article |
| id | doaj-art-2361caefd2674f268b1483d7ee8de2c0 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-2361caefd2674f268b1483d7ee8de2c02025-08-20T03:29:35ZengIEEEIEEE Access2169-35362025-01-011310575310576510.1109/ACCESS.2025.358082411039621CLF3D: A Coarse-Labeling Framework to Facilitate 3D Object Detection in Point CloudsNuo Cheng0https://orcid.org/0000-0002-4748-4554Chuanyu Luo1https://orcid.org/0000-0001-8496-8550Han Li2Sikun Ma3Shengguang Lei4Pu Li5https://orcid.org/0000-0001-6481-9961Process Optimization Group, Technische Universität Ilmenau, Ilmenau, GermanyProcess Optimization Group, Technische Universität Ilmenau, Ilmenau, GermanyLiangDao GmbH, Berlin, GermanyLiangDao GmbH, Berlin, GermanyLiangDao GmbH, Berlin, GermanyProcess Optimization Group, Technische Universität Ilmenau, Ilmenau, GermanyTremendous scenarios have to be considered for autonomous driving, leading to extremely large amount of point cloud data which need to be labeled for model training. Manually labeling such data is labor-intensive and highly expensive. In this paper, we propose CLF3D, a simple and effective coarse-labeling framework designed to improve existing automated labeling methods by fully leveraging scene-specific information in the unlabeled data to significantly enhance detection accuracy. Specifically, CLF3D first utilizes a pre-trained model to generate initial pseudo-labels, which are subsequently refined using a two-stage filtering strategy in combination with an instance bank built from high-quality annotated instances. These refined pseudo-labels are then used to fine-tune the model, progressively improving its detection performance on unlabeled data. Through iterative refinement of pseudo-labels, the model parameters, and the instance bank, CLF3D continuously improves label quality and accuracy. Experimental results demonstrate that the proposed method improves the detection accuracy by up to 14% compared to the originally pre-trained model across datasets of various sizes. This means our approach can reduce 14% of the manual workload for labeling point cloud data in comparison to the existing methods.https://ieeexplore.ieee.org/document/11039621/Label efficiencyobject detectionpoint cloudautonomous drivingKITTI |
| spellingShingle | Nuo Cheng Chuanyu Luo Han Li Sikun Ma Shengguang Lei Pu Li CLF3D: A Coarse-Labeling Framework to Facilitate 3D Object Detection in Point Clouds IEEE Access Label efficiency object detection point cloud autonomous driving KITTI |
| title | CLF3D: A Coarse-Labeling Framework to Facilitate 3D Object Detection in Point Clouds |
| title_full | CLF3D: A Coarse-Labeling Framework to Facilitate 3D Object Detection in Point Clouds |
| title_fullStr | CLF3D: A Coarse-Labeling Framework to Facilitate 3D Object Detection in Point Clouds |
| title_full_unstemmed | CLF3D: A Coarse-Labeling Framework to Facilitate 3D Object Detection in Point Clouds |
| title_short | CLF3D: A Coarse-Labeling Framework to Facilitate 3D Object Detection in Point Clouds |
| title_sort | clf3d a coarse labeling framework to facilitate 3d object detection in point clouds |
| topic | Label efficiency object detection point cloud autonomous driving KITTI |
| url | https://ieeexplore.ieee.org/document/11039621/ |
| work_keys_str_mv | AT nuocheng clf3dacoarselabelingframeworktofacilitate3dobjectdetectioninpointclouds AT chuanyuluo clf3dacoarselabelingframeworktofacilitate3dobjectdetectioninpointclouds AT hanli clf3dacoarselabelingframeworktofacilitate3dobjectdetectioninpointclouds AT sikunma clf3dacoarselabelingframeworktofacilitate3dobjectdetectioninpointclouds AT shengguanglei clf3dacoarselabelingframeworktofacilitate3dobjectdetectioninpointclouds AT puli clf3dacoarselabelingframeworktofacilitate3dobjectdetectioninpointclouds |