Three pillars improving vision foundation model distillation for lidar

G Puy, S Gidaris, A Boulch, O Siméoni… - Proceedings of the …, 2024 - openaccess.thecvf.com
Self-supervised image backbones can be used to address complex 2D tasks (eg semantic
segmentation object discovery) very efficiently and with little or no downstream supervision …

Segment any point cloud sequences by distilling vision foundation models

Y Liu, L Kong, J Cen, R Chen… - Advances in …, 2024 - proceedings.neurips.cc
Recent advancements in vision foundation models (VFMs) have opened up new
possibilities for versatile and efficient visual perception. In this work, we introduce Seal, a …

Domain generalization for semantic segmentation: A survey

TH Rafi, R Mahjabin, E Ghosh, YW Ko… - Artificial Intelligence …, 2024 - Springer
Deep neural networks (DNNs) have proven explicit contributions in making autonomous
driving cars and related tasks such as semantic segmentation, motion tracking, object …

Dg-pic: Domain generalized point-in-context learning for point cloud understanding

J Jiang, Q Zhou, Y Li, X Lu, M Wang, L Ma… - … on Computer Vision, 2025 - Springer
Recent point cloud understanding research suffers from performance drops on unseen data,
due to the distribution shifts across different domains. While recent studies use Domain …

Unimix: Towards domain adaptive and generalizable lidar semantic segmentation in adverse weather

H Zhao, J Zhang, Z Chen, S Zhao… - Proceedings of the …, 2024 - openaccess.thecvf.com
LiDAR semantic segmentation (LSS) is a critical task in autonomous driving and has
achieved promising progress. However prior LSS methods are conventionally investigated …

Dgmamba: Domain generalization via generalized state space model

S Long, Q Zhou, X Li, X Lu, C Ying, Y Luo… - Proceedings of the …, 2024 - dl.acm.org
Domain generalization (DG) aims at solving distribution shift problems in various scenes.
Existing approaches are based on Convolution Neural Networks (CNNs) or Vision …

Multi-Space Alignments Towards Universal LiDAR Segmentation

Y Liu, L Kong, X Wu, R Chen, X Li… - Proceedings of the …, 2024 - openaccess.thecvf.com
A unified and versatile LiDAR segmentation model with strong robustness and
generalizability is desirable for safe autonomous driving perception. This work presents …

A survey of label-efficient deep learning for 3D point clouds

A Xiao, X Zhang, L Shao, S Lu - IEEE Transactions on Pattern …, 2024 - ieeexplore.ieee.org
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 …

CoDA: Instructive chain-of-domain adaptation with severity-aware visual prompt tuning

Z Gong, F Li, Y Deng, D Bhattacharjee, X Ma… - … on Computer Vision, 2024 - Springer
Abstract Unsupervised Domain Adaptation (UDA) aims to adapt models from labeled source
domains to unlabeled target domains. When adapting to adverse scenes, existing UDA …

4d contrastive superflows are dense 3d representation learners

X Xu, L Kong, H Shuai, W Zhang, L Pan, K Chen… - … on Computer Vision, 2025 - Springer
In the realm of autonomous driving, accurate 3D perception is the foundation. However,
developing such models relies on extensive human annotations–a process that is both …