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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add masked cross-modal removal and prediction (xMRP) (ablation) | xMUDA · USA/Singapore | 2D mIoU: 59.3 -> 62.0 | Improved |
| Add masked cross-modal removal and prediction (xMRP) (ablation) | xMUDA · USA/Singapore | 3D mIoU: 52.0 -> 57.6 | Improved |
| Use single-modality removal and prediction rather than cross-modal prediction (ablation) | xMUDA · USA/Singapore | 2D mIoU: 62.0 -> 59.4 | Hurt |
| Use a single MLP prediction head instead of a linear head (ablation) | Mx2M · USA/Singapore | 2D mIoU: 61.4 -> 62.0 | Improved |
| Use a single MLP prediction head instead of a linear head (ablation) | Mx2M · USA/Singapore | 3D mIoU: 56.5 -> 57.6 | Improved |
| Add DxMF to segmentation prediction heads (ablation) | Mx2M · USA/Singapore | 3D mIoU: 57.6 -> 64.2 | Improved |
| Apply DxMF to mimicking heads rather than prediction heads (ablation) | Mx2M · USA/Singapore | 3D mIoU: 64.2 -> 52.4 | Hurt |
| Apply DxMF to xMRP heads rather than prediction heads (ablation) | Mx2M · USA/Singapore | 3D mIoU: 64.2 -> 50.8 | Hurt |
| Add pseudo-label supervision | Mx2M · Day/Night | Avg mIoU: 49.8 -> 54.6 | Improved |
| Add pseudo-label supervision | Mx2M · A2D2/SemanticKITTI | Avg mIoU: 47.1 -> 51.3 | Improved |
| Add pseudo-label supervision | Mx2M · USA/Singapore | Avg mIoU: 64.2 -> 67.4 | Improved |
| Add adversarial learning (AUDA-style AL) | Mx2M · USA/Singapore | 2D mIoU: 64.1 -> 56.26 | Hurt |
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.
- xMUDA — xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation (CVPR 2020) · better on 3 of 3 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
- Sparse-to-Dense Feature Matching: Intra and Inter Domain Cross-Modal Learning in Domain Adaptation for 3D Semantic Segmentation (ICCV 2021 · similarity 0.93)
- Cross-Modal Learning for Domain Adaptation in 3D Semantic Segmentation (TPAMI 2022 · similarity 0.92)
- XMask3D: Cross-modal Mask Reasoning for Open Vocabulary 3D Semantic Segmentation (NeurIPS 2024 · similarity 0.89)
- UniDSeg: Unified Cross-Domain 3D Semantic Segmentation via Visual Foundation Models Prior (NeurIPS 2024 · similarity 0.88)
- Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation (NeurIPS 2024 · similarity 0.86)
- Omni-Query Active Learning for Source-Free Domain Adaptive Cross-Modality 3D Semantic Segmentation (AAAI 2025 · similarity 0.85)
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.
