AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation

Maximilian Jaritz, Tuan-Hung Vu, Raoul de Charette, Emilie Wirbel, Patrick Perez

CVPR 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 228 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add cross-modal learning to source-only training2D stream, USA/Singapore · USA/Singapore target testmIoUImproved
Add cross-modal learning to source-only training3D stream, USA/Singapore · USA/Singapore target testmIoUImproved
Add pseudo-label self-training to xMUDAxMUDA · USA/Singapore target testmIoU (softmax avg): 62.7 -> 63.2Improved
Add pseudo-label self-training to xMUDAxMUDA · Day/Night target testmIoU (softmax avg): 50.0 -> 50.8Improved
Add pseudo-label self-training to xMUDAxMUDA · A2D2/SemanticKITTI target testmIoU (softmax avg): 42.9 -> 49.1Improved
Add pseudo-label self-training to xMUDAxMUDA · Day/Night target testmIoU (softmax avg): 50.0 -> 50.8; xMUDA_PL does not achieve the best scoreMixed
Train the mimicry head with cross-modal loss on source as well as target, rather than target only (ablation)xMUDA · USA/SingaporemIoU (2D): 4.8 mIoUImproved
Train the mimicry head with cross-modal loss on source as well as target, rather than target only (ablation)xMUDA · USA/SingaporemIoU (3D): 4.4 mIoUImproved
Use separate main and mimicry segmentation heads instead of a single shared head (ablation)xMUDA · USA/SingaporemIoUImproved
Add cross-modal loss during supervised oracle training (ablation)Oracle 2D stream · USA/Singapore oraclemIoU: 65.8 -> 66.4Improved
Add cross-modal loss during supervised oracle training (ablation)Oracle 3D stream · USA/Singapore oraclemIoU: 63.2 -> 63.8Improved
Add cross-modal loss during supervised oracle training (ablation)Oracle softmax average · USA/Singapore oraclemIoU: 71.1 -> 71.6Improved

Later papers that compared with this method

4 later accepted papers report xMUDA as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy