Research map / Detection and segmentation / Open-set and few-shot detection
Deeply Seeking Boundary for Lunar Regolith Segmentation
Yifeng Wang, Lingxin Wang, Lu Zhang, Yang Li, Chao Xu, Weiwei Zhang, Junyue Tang, Yanhong Zheng, Yong Pang, Shengyuan Jiang, Yi Zhao, Zongquan Deng
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 |
|---|---|---|---|
| use HiFi-LoRA initialization instead of standard LoRA (ablation) | SAM + LoRA · LRSD (lunar regolith) | HD95: 11.18 -> 6.15 | Improved |
| use HiFi-LoRA initialization instead of standard LoRA (ablation) | SAM + LoRA · LRSD (lunar regolith) | mIoU: 84.3 -> 87.0 | Improved |
| add WEM regularizer (ablation) | SAM + LoRA · LRSD (lunar regolith) | HD95: 11.18 -> 7.31 | Improved |
| add WEM regularizer on top of HiFi-LoRA (ablation) | HiFi-LoRA SAM · LRSD (lunar regolith) | HD95: 6.15 -> 4.53 | Improved |
| add HiFi-LoRA on top of WEM (ablation) | WEM SAM · LRSD (lunar regolith) | mIoU: 86.8 -> 89.1 | Improved |
| use MedSAM prior instead of SAM when more training data is available | HiFi-LoRA + WEM · LRSD (lunar regolith) | HD95 | Hurt |
| use Mask2Former-style stronger regional architectures vs HiFi-LoRA | SegMAN · LRSD (lunar regolith) | mIoU: 87.5 -> 89.1 | Mixed |
Closest papers by meaning
- Mars-Bench: A Benchmark for Evaluating Foundation Models for Mars Science Tasks (NeurIPS 2025 · similarity 0.85)
- SatSynth: Augmenting Image-Mask Pairs through Diffusion Models for Aerial Semantic Segmentation (CVPR 2024 · similarity 0.83)
- ROS-SAM: High-Quality Interactive Segmentation for Remote Sensing Moving Object (CVPR 2025 · similarity 0.82)
- Phaedra: Learning High-Fidelity Discrete Tokenization for the Physical Sciences (NeurIPS 2026 · similarity 0.82)
- STAR-Edge: Structure-aware Local Spherical Curve Representation for Thin-walled Edge Extraction from Unstructured Point Clouds (CVPR 2025 · similarity 0.81)
- Towards Automated Petrography (NeurIPS 2025 · similarity 0.81)
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.
