Research map / Point clouds / Segmentation and detection
Perturbed Self-Distillation: Weakly Supervised Large-Scale Point Cloud Semantic Segmentation
Yachao Zhang, Yanyun Qu, Yuan Xie, Zonghao Li, Shanshan Zheng, Cuihua 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 point perturbation as plain data augmentation (ablation) | RandLA-Net baseline · S3DIS Area-5 (1pt) | mIoU: 40.7 -> 41.1 | No clear effect |
| add point perturbation as plain data augmentation (ablation) | RandLA-Net baseline · S3DIS Area-5 (1%) | mIoU: 58.6 -> 59.9 | No clear effect |
| add perturbed self-distillation (ablation) | RandLA-Net baseline · S3DIS Area-5 (1pt) | mIoU: 40.7 -> 46.9 | Improved |
| add perturbed self-distillation (ablation) | RandLA-Net baseline · S3DIS Area-5 (1%) | mIoU: 58.6 -> 62.0 | Improved |
| add perturbed self-distillation (ablation) | RandLA-Net baseline · S3DIS Area-5 (fully supervised) | mIoU: 63.0 -> 63.9 | Improved |
| add context-aware module (ablation) | PSD self-distillation · S3DIS Area-5 (1pt) | mIoU: 46.9 -> 48.2 | Improved |
| add context-aware module (ablation) | PSD self-distillation · S3DIS Area-5 (1%) | mIoU: 62.0 -> 63.5 | Improved |
| add context-aware module (ablation) | PSD self-distillation · S3DIS Area-5 (fully supervised) | mIoU: 63.9 -> 65.1 | Improved |
| add full PSD (self-distillation + CAM) (ablation) | RandLA-Net baseline · S3DIS Area-5 (1% labels) | mIoU: 58.6 -> 63.5 | Improved |
| use PointNet++ backbone with PSD instead of Xu and Lee at lower label rate (ablation) | PSD+PN2 · S3DIS Area-5 (1% labels) | mIoU: 48.0 -> 51.0 | Improved |
| add PSD to RandLA-Net in weak 1pt setting vs Xu and Lee with more labels (ablation) | PSD · S3DIS Area-5 (1pt) | mIoU: 44.5 -> 48.2 | Improved |
| add PSD training cost (perturbed branch) (ablation) | RandLA-Net · S3DIS training time | training time (s/epoch): 216 -> 302 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- RandLA-Net — RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds (CVPR 2020) · better on 0 of 1 shared result
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
- Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud (AAAI 2021 · similarity 0.91)
- Weakly Supervised Semantic Point Cloud Segmentation: Towards 10x Fewer Labels (CVPR 2020 · similarity 0.90)
- SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds (ECCV 2022 · similarity 0.90)
- Weakly Supervised Point Cloud Semantic Segmentation via Artificial Oracle (CVPR 2024 · similarity 0.89)
- Less Is More: Label Recommendation for Weakly Supervised Point Cloud Semantic Segmentation (AAAI 2024 · similarity 0.88)
- Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentation (NeurIPS 2024 · similarity 0.87)
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.
