SC3D: Label-Efficient Outdoor 3D Object Detection via Single Click Annotation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xia, Qiming, Lin, Hongwei, Ye, Wei, Wu, Hai, Luo, Yadan, Wang, Cheng, Wen, Chenglu
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916481378287616
author Xia, Qiming
Lin, Hongwei
Ye, Wei
Wu, Hai
Luo, Yadan
Wang, Cheng
Wen, Chenglu
author_facet Xia, Qiming
Lin, Hongwei
Ye, Wei
Wu, Hai
Luo, Yadan
Wang, Cheng
Wen, Chenglu
contents LiDAR-based outdoor 3D object detection has received widespread attention. However, training 3D detectors from the LiDAR point cloud typically relies on expensive bounding box annotations. This paper presents SC3D, an innovative label-efficient method requiring only a single coarse click on the bird's eye view of the 3D point cloud for each frame. A key challenge here is the absence of complete geometric descriptions of the target objects from such simple click annotations. To address this issue, our proposed SC3D adopts a progressive pipeline. Initially, we design a mixed pseudo-label generation module that expands limited click annotations into a mixture of bounding box and semantic mask supervision. Next, we propose a mix-supervised teacher model, enabling the detector to learn mixed supervision information. Finally, we introduce a mixed-supervised student network that leverages the teacher model's generalization ability to learn unclicked instances.Experimental results on the widely used nuScenes and KITTI datasets demonstrate that our SC3D with only coarse clicks, which requires only 0.2% annotation cost, achieves state-of-the-art performance compared to weakly-supervised 3D detection methods.The code will be made publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2408_08092
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SC3D: Label-Efficient Outdoor 3D Object Detection via Single Click Annotation
Xia, Qiming
Lin, Hongwei
Ye, Wei
Wu, Hai
Luo, Yadan
Wang, Cheng
Wen, Chenglu
Computer Vision and Pattern Recognition
Artificial Intelligence
LiDAR-based outdoor 3D object detection has received widespread attention. However, training 3D detectors from the LiDAR point cloud typically relies on expensive bounding box annotations. This paper presents SC3D, an innovative label-efficient method requiring only a single coarse click on the bird's eye view of the 3D point cloud for each frame. A key challenge here is the absence of complete geometric descriptions of the target objects from such simple click annotations. To address this issue, our proposed SC3D adopts a progressive pipeline. Initially, we design a mixed pseudo-label generation module that expands limited click annotations into a mixture of bounding box and semantic mask supervision. Next, we propose a mix-supervised teacher model, enabling the detector to learn mixed supervision information. Finally, we introduce a mixed-supervised student network that leverages the teacher model's generalization ability to learn unclicked instances.Experimental results on the widely used nuScenes and KITTI datasets demonstrate that our SC3D with only coarse clicks, which requires only 0.2% annotation cost, achieves state-of-the-art performance compared to weakly-supervised 3D detection methods.The code will be made publicly available.
title SC3D: Label-Efficient Outdoor 3D Object Detection via Single Click Annotation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2408.08092