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

October 16, 2020 Β· Declared Dead Β· πŸ› International Conference on 3D Vision

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Cristiano Saltori, StΓ©phane LathuiliΓ©re, Nicu Sebe, Elisa Ricci, Fabio Galasso arXiv ID 2010.08243 Category cs.CV: Computer Vision Citations 36 Venue International Conference on 3D Vision Last Checked 6 months ago
Abstract
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Computer Vision

πŸŒ… πŸŒ… Old Age

Fast R-CNN

Ross Girshick

cs.CV πŸ› ICCV πŸ“š 27.7K cites 11 years ago

Died the same way β€” πŸ‘» Ghosted