AI Paper Atlas

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

Mx2M: Masked Cross-Modality Modeling in Domain Adaptation for 3D Semantic Segmentation

Boxiang Zhang, Zunran Wang, Yonggen Ling, Yuanyuan Guan, Shenghao Zhang, Wenhui Li

AAAI 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 12 citations (OpenAlex)

Read the paperCheck 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 masked cross-modal removal and prediction (xMRP) (ablation)xMUDA · USA/Singapore2D mIoU: 59.3 -> 62.0Improved
Add masked cross-modal removal and prediction (xMRP) (ablation)xMUDA · USA/Singapore3D mIoU: 52.0 -> 57.6Improved
Use single-modality removal and prediction rather than cross-modal prediction (ablation)xMUDA · USA/Singapore2D mIoU: 62.0 -> 59.4Hurt
Use a single MLP prediction head instead of a linear head (ablation)Mx2M · USA/Singapore2D mIoU: 61.4 -> 62.0Improved
Use a single MLP prediction head instead of a linear head (ablation)Mx2M · USA/Singapore3D mIoU: 56.5 -> 57.6Improved
Add DxMF to segmentation prediction heads (ablation)Mx2M · USA/Singapore3D mIoU: 57.6 -> 64.2Improved
Apply DxMF to mimicking heads rather than prediction heads (ablation)Mx2M · USA/Singapore3D mIoU: 64.2 -> 52.4Hurt
Apply DxMF to xMRP heads rather than prediction heads (ablation)Mx2M · USA/Singapore3D mIoU: 64.2 -> 50.8Hurt
Add pseudo-label supervisionMx2M · Day/NightAvg mIoU: 49.8 -> 54.6Improved
Add pseudo-label supervisionMx2M · A2D2/SemanticKITTIAvg mIoU: 47.1 -> 51.3Improved
Add pseudo-label supervisionMx2M · USA/SingaporeAvg mIoU: 64.2 -> 67.4Improved
Add adversarial learning (AUDA-style AL)Mx2M · USA/Singapore2D mIoU: 64.1 -> 56.26Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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