Semantic segmentation of LiDAR point clouds is an important task in autonomous driving.
However, training deep models via conventional supervised methods requires large …

We study the problem of 3D semantic segmentation from raw point clouds. Unlike existing
methods which primarily rely on a large amount of human annotations for training neural …

Labelling point clouds fully is highly time-consuming and costly. As larger point cloud
datasets with billions of points become more common, we ask whether the full annotation is …

Self-training has greatly facilitated domain adaptive semantic segmentation, which iteratively
generates pseudo labels on unlabeled target data and retrains the network. However …

We propose LiDAL, a novel active learning method for 3D LiDAR semantic segmentation by
exploiting inter-frame uncertainty among LiDAR frames. Our core idea is that a well-trained …

Active learning, a label-efficient paradigm, empowers models to interactively query an oracle
for labeling new data. In the realm of LiDAR semantic segmentation, the challenges stem …

Deep learning has achieved widespread success in medical image analysis, leading to an
increasing demand for large-scale expert-annotated medical image datasets. Yet, the high …

Impressive performance on point cloud semantic segmentation has been achieved by fully-
supervised methods with large amounts of labelled data. As it is labour-intensive to acquire …

In the past decade, deep neural networks have achieved significant progress in point cloud
learning. However, collecting large-scale precisely-annotated point clouds is extremely …

Semantic segmentation plays an important role in understanding 3D scenes, recognizing
objects, and reconstructing 3D models. However, this predominantly requires the training of …