Current high-performance semantic segmentation models are purely data-driven sub-
symbolic approaches and blind to the structured nature of the visual world. This is in stark …

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 …

A unified and versatile LiDAR segmentation model with strong robustness and
generalizability is desirable for safe autonomous driving perception. This work presents …

Abstract 3D synthetic-to-real unsupervised domain adaptive segmentation is crucial to
annotating new domains. Self-training is a competitive approach for this task but its …

Domain adaptive LiDAR point cloud segmentation aims to learn an effective target
segmentation model from labelled source data and unlabelled target data, which has …

Learning models on one labeled dataset that generalize well on another domain is a difficult
task, as several shifts might happen between the data domains. This is notably the case for …

Domain generalization (DG) aims to train a model with access to a limited number of source
domains for generalizing it across various unseen target domains. The key to solving the DG …

This paper tackles the domain adaptation problem in point cloud semantic segmentation
which performs adaptation from a fully labeled domain (source domain) to an unlabeled …

Learning models on one labeled dataset that generalize well on another domain is a difficult
task, as several shifts might happen between the data domains. This is notably the case for …

Aerial-view human detection has a large demand for large-scale data to capture more
diverse human appearances compared to ground-view human detection. Therefore …