Research map / Point clouds / Segmentation and detection
Guided Point Contrastive Learning for Semi-Supervised Point Cloud Semantic Segmentation
Li Jiang, Shaoshuai Shi, Zhuotao Tian, Xin Lai, Shu Liu, Chi-Wing Fu, Jiaya Jia
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 unlabeled data with guided point contrastive loss | Sup-only U-Net · ScanNet V2 val (5% labeled) | mIoU (%): 48.1 -> 54.8 | Improved |
| add unlabeled data with guided point contrastive loss | Sup-only U-Net · S3DIS Area 5 (5% labeled) | mIoU (%): 45.0 -> 53.0 | Improved |
| add unlabeled data with guided point contrastive loss | Sup-only U-Net · SemanticKITTI val (5% labeled) | mIoU (%): 34.8 -> 41.8 | Improved |
| add guided contrastive loss as auxiliary on 100% labeled data | Sup-only U-Net · ScanNet V2 val (100% labeled) | mIoU (%): 72.9 -> 74.0 | Improved |
| add test set to unlabeled data (transductive) | Semi-sup model · SemanticKITTI test (100% labeled) | mIoU (%): 67.7 -> 70.2 | Improved |
| add pseudo-label guidance to point contrastive loss (ablation) | PointInfoNCE · ScanNet V2 val (20% labeled) | mIoU (%): 64.4 -> 65.9 | Improved |
| add confidence guidance (ablation) | Model-a · ScanNet V2 val (20% labeled) | mIoU (%): 65.9 -> 66.4 | Improved |
| add category-balanced sampling (ablation) | Model-b · ScanNet V2 val (20% labeled) | mIoU (%): 66.4 -> 66.7 | Improved |
| add category-balanced sampling instead of random sampling (ablation) | Full model · SemanticKITTI val (20% labeled) | mIoU (%): 57.1 -> 58.8 | Improved |
| use partial multi-view instead of random crop (ablation) | Full model · ScanNet V2 val (20% labeled) | mIoU (%): 66.7 -> 63.2 | Hurt |
| add projector before contrastive loss (ablation) | Full model · ScanNet V2 val (20% labeled) | mIoU (%): 65.0 -> 66.7 | Improved |
| use guided contrastive learning rather than self-training (ablation) | Semi-sup strategies · ScanNet V2 val (20% labeled) | mIoU (%): 65.5 -> 66.7 | Improved |
Closest papers by meaning
- SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network (AAAI 2021 · similarity 0.91)
- Density-Guided Semi-Supervised 3D Semantic Segmentation with Dual-Space Hardness Sampling (CVPR 2024 · similarity 0.91)
- Quantity-Quality Enhanced Self-Training Network for Weakly Supervised Point Cloud Semantic Segmentation (TPAMI 2025 · similarity 0.91)
- Less Is More: Label Recommendation for Weakly Supervised Point Cloud Semantic Segmentation (AAAI 2024 · similarity 0.90)
- Weakly Supervised Point Cloud Semantic Segmentation via Artificial Oracle (CVPR 2024 · similarity 0.89)
- Multi-Modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation (AAAI 2024 · similarity 0.89)
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.
