Instance-Level Strong Augmentation for Semi-Supervised 3D Object Detection / under review at CVPR 2025
Proposed an instance-level strong augmentation strategy for semi-supervised 3D object detection to fully exploit instance-specific information for accurate object detection in 3D environments.
Nov 16, 2024
ATSS3D: Adaptive Threshold for Semi-Supervised 3D Object Detection / under review at CVPR 2025
Proposed a probabilistic decision adaptive thresholding method for semi-supervised 3D object detection, which dynamically adjusts thresholds based on learned states at scene, batch, and class levels, effectively improving pseudo-label quality and detection performance on ScanNet and SUN RGB-D.
Nov 16, 2024