REVIEW 1 cited by
ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
We present a new domain adaptive self-training pipeline, named ST3D, for unsupervised domain adaptation on 3D object detection from point clouds. First, we pre-train the 3D detector on the source domain with our proposed random object scaling strategy for mitigating the negative effects of source domain bias. Then, the detector is iteratively improved on the target domain by alternatively conducting two steps, which are the pseudo label updating with the developed quality-aware triplet memory bank and the model training with curriculum data augmentation. These specific designs for 3D object detection enable the detector to be trained with consistent and high-quality pseudo labels and to avoid overfitting to the large number of easy examples in pseudo labeled data. Our ST3D achieves state-of-the-art performance on all evaluated datasets and even surpasses fully supervised results on KITTI 3D object detection benchmark. Code will be available at https://github.com/CVMI-Lab/ST3D.
Forward citations
Cited by 1 Pith paper
-
3D Can Be Explored In 2D: Pseudo-Label Generation for LiDAR Point Clouds Using Sensor-Intensity-Based 2D Semantic Segmentation
A pipeline segments aligned LiDAR point clouds by rendering intensity-colored 2D views, applying a camera-domain 2D segmentation model, and voting back-projected labels, producing competitive pseudo-labels for unsuper...
Discussion (0). Continue with ORCID to comment.