SF-UDA^3D: Source-Free Unsupervised Domain Adaptation for LiDAR-Based 3D Object Detection

by   Cristiano Saltori, et al.

3D object detectors based only on LiDAR point clouds hold the state-of-the-art on modern street-view benchmarks. However, LiDAR-based detectors poorly generalize across domains due to domain shift. In the case of LiDAR, in fact, domain shift is not only due to changes in the environment and in the object appearances, as for visual data from RGB cameras, but is also related to the geometry of the point clouds (e.g., point density variations). This paper proposes SF-UDA^3D, the first Source-Free Unsupervised Domain Adaptation (SF-UDA) framework to domain-adapt the state-of-the-art PointRCNN 3D detector to target domains for which we have no annotations (unsupervised), neither we hold images nor annotations of the source domain (source-free). SF-UDA^3D is novel on both aspects. Our approach is based on pseudo-annotations, reversible scale-transformations and motion coherency. SF-UDA^3D outperforms both previous domain adaptation techniques based on features alignment and state-of-the-art 3D object detection methods which additionally use few-shot target annotations or target annotation statistics. This is demonstrated by extensive experiments on two large-scale datasets, i.e., KITTI and nuScenes.



There are no comments yet.


page 4

page 7


Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection

3D object detection networks tend to be biased towards the data they are...

SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation

In autonomous driving, a LiDAR-based object detector should perform reli...

FAST3D: Flow-Aware Self-Training for 3D Object Detectors

In the field of autonomous driving, self-training is widely applied to m...

Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency

Deep learning-based 3D object detection has achieved unprecedented succe...

Cycle and Semantic Consistent Adversarial Domain Adaptation for Reducing Simulation-to-Real Domain Shift in LiDAR Bird's Eye View

The performance of object detection methods based on LiDAR information i...

See Eye to Eye: A Lidar-Agnostic 3D Detection Framework for Unsupervised Multi-Target Domain Adaptation

Sampling discrepancies between different manufacturers and models of lid...

LiDAR-assisted Large-scale Privacy Protection in Street-view Cycloramas

Recently, privacy has a growing importance in several domains, especiall...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.