Three pillars improving vision foundation model distillation for lidar
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 …
segmentation object discovery) very efficiently and with little or no downstream supervision …
Segment any point cloud sequences by distilling vision foundation models
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 …
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 …
driving cars and related tasks such as semantic segmentation, motion tracking, object …
Dg-pic: Domain generalized point-in-context learning for point cloud understanding
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 …
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
LiDAR semantic segmentation (LSS) is a critical task in autonomous driving and has
achieved promising progress. However prior LSS methods are conventionally investigated …
achieved promising progress. However prior LSS methods are conventionally investigated …
Dgmamba: Domain generalization via generalized state space model
Domain generalization (DG) aims at solving distribution shift problems in various scenes.
Existing approaches are based on Convolution Neural Networks (CNNs) or Vision …
Existing approaches are based on Convolution Neural Networks (CNNs) or Vision …
Multi-Space Alignments Towards Universal LiDAR Segmentation
A unified and versatile LiDAR segmentation model with strong robustness and
generalizability is desirable for safe autonomous driving perception. This work presents …
generalizability is desirable for safe autonomous driving perception. This work presents …
A survey of label-efficient deep learning for 3D point clouds
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 …
learning. However, collecting large-scale precisely-annotated point clouds is extremely …
CoDA: Instructive chain-of-domain adaptation with severity-aware visual prompt tuning
Abstract Unsupervised Domain Adaptation (UDA) aims to adapt models from labeled source
domains to unlabeled target domains. When adapting to adverse scenes, existing UDA …
domains to unlabeled target domains. When adapting to adverse scenes, existing UDA …
4d contrastive superflows are dense 3d representation learners
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 …
developing such models relies on extensive human annotations–a process that is both …