Research map / Point clouds / Segmentation and detection
Sparse-to-Dense Feature Matching: Intra and Inter Domain Cross-Modal Learning in Domain Adaptation for 3D Semantic Segmentation
Duo Peng, Yinjie Lei, Wen Li, Pingping Zhang, Yulan Guo
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 DsCML to baseline (ablation) | xMUDA-style 2D/3D network · all five DA settings | mIoU: 2D +3.2 to +10, 3D +3.4 to +7.8, Avg +2.3 to +3.7 | Improved |
| add CMAL on top of DsCML (ablation) | DsCML · all settings | mIoU: over 1.1 on 2D and over 2.1 on 3D | Improved |
| add pseudo-labeling to DsCML+CMAL (ablation) | DsCML + CMAL · USA->Singapore (nuScenes) | 3D mIoU: 55.6 -> 56.3 | Improved |
| use sparse-to-dense square patch (sCML) instead of one-to-one matching (CML) (ablation) | DsCML · USA->Singapore (nuScenes) | 3D mIoU: 51.7 -> 52.5 | Improved |
| use deformable patch (DsCML) instead of square patch (sCML) (ablation) | DsCML · A2D2->SemanticKITTI | 3D mIoU: 44.3 -> 45.1 | Improved |
| use max/min sparse-to-dense loss instead of patch-mean loss (ablation) | DsCML · A2D2->SemanticKITTI | 2D mIoU: 37.6 -> 39.6 | Improved |
| add sparse-to-dense loss L_std (ablation) | DsCML · USA->Singapore (nuScenes) | 2D mIoU: 53.4 -> 61.3 | Improved |
| use cross-modal alignment (S2D<->T3D, S3D<->T2D) instead of inter-modal alignment (S2D<->T2D) (ablation) | CMAL · USA->Singapore (Lidarseg) | 3D mIoU: 54.9 -> 56.2 | Improved |
| use both alignment schemes together instead of cross-modal only (ablation) | CMAL · USA->Singapore (Lidarseg) | 3D mIoU: 56.2 -> 55.3 | Hurt |
Closest papers by meaning
- Cross-Modal Learning for Domain Adaptation in 3D Semantic Segmentation (TPAMI 2022 · similarity 0.95)
- Cross-Modal Contrastive Learning for Domain Adaptation in 3D Semantic Segmentation (AAAI 2023 · similarity 0.94)
- Mx2M: Masked Cross-Modality Modeling in Domain Adaptation for 3D Semantic Segmentation (AAAI 2023 · similarity 0.93)
- BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation (ICCV 2023 · similarity 0.92)
- UniDSeg: Unified Cross-Domain 3D Semantic Segmentation via Visual Foundation Models Prior (NeurIPS 2024 · similarity 0.89)
- Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation (NeurIPS 2024 · similarity 0.88)
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.
