Semi-supervised 3D Object Detection via Adaptive Pseudo-Labeling
3D object detection is an important task in computer vision. Most existing methods require a large number of high-quality 3D annotations, which are expensive to collect. Especially for outdoor scenes, the problem becomes more severe due to the sparseness of the point cloud and the complexity of urban scenes. Semi-supervised learning is a promising technique to mitigate the data annotation issue. Inspired by this, we propose a novel semi-supervised framework based on pseudo-labeling for outdoor 3D object detection tasks. We design the Adaptive Class Confidence Selection module (ACCS) to generate high-quality pseudo-labels. Besides, we propose Holistic Point Cloud Augmentation (HPCA) for unlabeled data to improve robustness. Experiments on the KITTI benchmark demonstrate the effectiveness of our method.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Object DetectionObjectobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
Density-Guided Dense Pseudo Label Selection For Semi-supervised Oriented Object Detection
Recently, dense pseudo-label, which directly selects pseudo labels from the original output of the teacher model without any complicated post-processing steps, has received considerable attention in semi-supervised objec…
Objectobject-detectionObject DetectionOriented Object Detection+2SOOD: Towards Semi-Supervised Oriented Object Detection
Semi-Supervised Object Detection (SSOD), aiming to explore unlabeled data for boosting object detectors, has become an active task in recent years. However, existing SSOD approaches mainly focus on horizontal objects, le…
Objectobject-detectionObject DetectionOriented Object Detection+2Learning Adaptive Pseudo-Label Selection for Semi-Supervised 3D Object Detection
Semi-supervised 3D object detection (SS3DOD) aims to reduce costly 3D annotations utilizing unlabeled data. Recent studies adopt pseudo-label-based teacher-student frameworks and demonstrate impressive performance. The m…
3D Object DetectionSemi-Supervised and Long-Tailed Object Detection with CascadeMatch
This paper focuses on long-tailed object detection in the semi-supervised learning setting, which poses realistic challenges, but has rarely been studied in the literature. We propose a novel pseudo-labeling-based detect…
Long-tailed Object DetectionObjectobject-detectionObject Detection+1PseudoProp: Robust Pseudo-Label Generation for Semi-Supervised Object Detection in Autonomous Driving Systems
Semi-supervised object detection methods are widely used in autonomous driving systems, where only a fraction of objects are labeled. To propagate information from the labeled objects to the unlabeled ones, pseudo-labels…
Autonomous DrivingObjectobject-detectionObject Detection+2