AI RESEARCH
Learning Adaptive Pseudo-Label Selection for Semi-Supervised 3D Object Detection
arXiv CS.CV
•
ArXi:2509.23880v3 Announce Type: replace 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 nstrate impressive performance. The main challenge of these frameworks is in selecting high-quality pseudo-labels from the teacher's predictions. Most previous methods, however, select pseudo-labels by comparing confidence scores over thresholds manually set. The latest works tackle the challenge either by dynamic thresholding or refining the quality of pseudo-labels.