PanDA is the first UDA method for multimodal 3D panoptic segmentation that improves robustness to single-modality degradation and pseudo-label completeness via asymmetric augmentation and dual-expert refinement.
Sess: Self- ensembling semi-supervised 3d object detection
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
A semi-supervised 3D object detection framework with a learnable module for adaptive pseudo-label selection via score fusion, context-aware thresholds, and soft supervision.
citing papers explorer
-
PanDA: Unsupervised Domain Adaptation for Multimodal 3D Panoptic Segmentation in Autonomous Driving
PanDA is the first UDA method for multimodal 3D panoptic segmentation that improves robustness to single-modality degradation and pseudo-label completeness via asymmetric augmentation and dual-expert refinement.
-
Learning Adaptive Pseudo-Label Selection for Semi-Supervised 3D Object Detection
A semi-supervised 3D object detection framework with a learnable module for adaptive pseudo-label selection via score fusion, context-aware thresholds, and soft supervision.