Research map / Detection and segmentation / Open-set and few-shot detection
On-the-fly Category Discovery for LiDAR Semantic Segmentation
Hyeonseong Kim, Sung-Hoon Yoon, Minseok Kim, Kuk-Jin Yoon
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 dual prototypical learning (hash prototypes) (ablation) | Hash-coding baseline · SemanticPOSS scenario-A, Strict-Hungarian, Known | mIoU (%): 25.12 -> 40.08 | Improved |
| add dual prototypical learning (hash prototypes) (ablation) | Hash-coding baseline · SemanticPOSS scenario-A, Strict-Hungarian, Unknown | mIoU (%): 11.98 -> 5.33 | Hurt |
| add dual prototypical learning (ablation) | SMILE · SemanticPOSS scenario-A, Strict-Hungarian, Known | mIoU (%): 35.26 -> 44.15 | Improved |
| add discrimination module on mixed representations (ablation) | Base + DPL · SemanticPOSS scenario-A, Strict-Hungarian, Unknown | mIoU (%): 5.33 -> 16.48 | Improved |
| add grouping module (ablation) | Base + DPL + DM · SemanticPOSS scenario-A, Strict-Hungarian, Unknown | mIoU (%): 16.48 -> 21.54 | Improved |
| add grouping module (ablation) | Base + DPL + DM · SemanticPOSS scenario-A, Strict-Hungarian, Known | mIoU (%): 48.24 -> 46.63 | Hurt |
| use full method versus SMILE | OCDSS · SemanticPOSS scenario-A, Strict-Hungarian, All | mIoU (%): 28.30 -> 40.23 | Improved |
| use full method versus SMILE on scenario-B | SemanticKITTI scenario-B · Greedy-Hungarian, Unknown | mIoU (%): 47.67 -> 42.12 | Hurt |
| simulate unknown classes via meta-learning (MLDG) | Baseline · SemanticKITTI scenario-A, Strict-Hungarian, Unknown | mIoU (%): 11.74 -> 9.74 | Hurt |
Closest papers by meaning
- Lidar Panoptic Segmentation in an Open World (IJCV 2024 · similarity 0.90)
- LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds (ECCV 2022 · similarity 0.90)
- Open-World Semantic Segmentation for LIDAR Point Clouds (ECCV 2022 · similarity 0.90)
- Temporal Consistent 3D LiDAR Representation Learning for Semantic Perception in Autonomous Driving (CVPR 2023 · similarity 0.89)
- HiLoTs: High-Low Temporal Sensitive Representation Learning for Semi-Supervised LiDAR Segmentation in Autonomous Driving (CVPR 2025 · similarity 0.88)
- No Thing, Nothing: Highlighting Safety-Critical Classes for Robust LiDAR Semantic Segmentation in Adverse Weather (CVPR 2025 · 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.
