Research map / Detection and segmentation / Open-set and few-shot detection
CrossCut: Cross-Patch Aware Interactive Segmentation for Remote Sensing Images
Zheng Lin, Nan Zhou, Yuhan Wang, Bojian Zhang
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 Cross-Patch Prompt Embedding (CPE) to the SimpleClick baseline (ablation) | CrossCut baseline · DeepGlobe test | mIoU@5 clicks: 55.25 -> 69.72 | Improved |
| add CPE (ablation) | CrossCut baseline · DeepGlobe test | NoC@80: 15.51 -> 13.30 | Improved |
| add CPE (ablation) | CrossCut baseline · Inria test | mIoU@5 clicks: 63.09 -> 82.60 | Improved |
| add CPE (ablation) | CrossCut baseline · iSAID val | mIoU@20 clicks: 71.82 -> 72.17 | Improved |
| add CPE (ablation) | CrossCut baseline · Inria test | NoC@80: 10.39 -> 5.00 | Improved |
| add Multi-Scale Division Fusion (MDF) on top of CPE (ablation) | CrossCut · iSAID val | mIoU@20 clicks: 72.17 -> 73.67 | Improved |
| add MDF on top of CPE (ablation) | CrossCut · iSAID val | NoC@80: 12.16 -> 11.63 | Improved |
| add MDF on top of CPE (ablation) | CrossCut · Inria test | NoC@80: 5.00 -> 4.68 | Improved |
| fuse 2x2, 3x3 and 4x4 patch results instead of the best single division (3x3) (ablation) | CrossCut · DeepGlobe test | mIoU@20 clicks: 79.17 -> 80.23 | Improved |
| use 3x3 division instead of 2x2 (ablation) | CrossCut · DeepGlobe test | mIoU@20 clicks: 77.72 -> 79.17 | Improved |
| use 4x4 division instead of 3x3 (ablation) | CrossCut · DeepGlobe test | mIoU@20 clicks: 79.17 -> 78.74 | Hurt |
| finetune SimpleClick on the three remote sensing datasets | SimpleClick · Inria test | NoC@70: 15.24 -> 4.88 | Improved |
Closest papers by meaning
- CrossEarth: Geospatial Vision Foundation Model for Domain Generalizable Remote Sensing Semantic Segmentation (TPAMI 2025 · similarity 0.88)
- ROS-SAM: High-Quality Interactive Segmentation for Remote Sensing Moving Object (CVPR 2025 · similarity 0.88)
- ReAttnCLIP: Training-Free Open-Vocabulary Remote Sensing Image Segmentation via Re-defined Attention in CLIP (CVPR 2026 · similarity 0.88)
- UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenes (CVPR 2026 · similarity 0.86)
- CrossEarth-Gate: Fisher-Guided Adaptive Tuning Engine for Efficient Adaptation of Cross-Domain Remote Sensing Semantic Segmentation (CVPR 2026 · similarity 0.86)
- ZoRI: Towards Discriminative Zero-Shot Remote Sensing Instance Segmentation (AAAI 2025 · similarity 0.84)
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.
