Research map / Detection and segmentation / Open-set and few-shot detection
SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 SAMRS segmentation pre-training with ImageNet initialization | UperNet with ViTAEv2-S · IsAID validation | mIOU: 65.79 -> 66.26 | Helped |
| Use SAMRS segmentation pre-training with ImageNet initialization | UperNet with ResNet-50 · ISPRS Potsdam | mF1: 90.07 -> 90.76 | Helped |
| Use SAMRS segmentation pre-training with ImageNet initialization | Mask2Former with ResNet-50 · ISPRS Potsdam | mF1: 86.87 -> 69.86 | Hurt |
| Use SAMRS segmentation pre-training | UNet with ResNet-50, 5% fine-tuning data · ISPRS Potsdam | mF1: +1.35 | Helped |
| Use SAMRS segmentation pre-training | UNet with ResNet-50, 5% fine-tuning data · IsAID validation | mIOU: +13.41 | Helped |
| Use H-Box instead of center point prompts | SAM · HRSC2016 testing set | mIOU_I: 16.14 -> 89.97 | Helped |
| Use RH-Box instead of R-Box mask prompts | SAM · HRSC2016 testing set | mIOU_I: 65.54 -> 88.85 | Helped |
| Add H-Box-M to H-Box (ablation) | SAM · HRSC2016 testing set | mIOU_I: 89.97 -> 74.21 | Hurt |
| Add center point to H-Box (ablation) | SAM · HRSC2016 testing set | mIOU_I: 89.97 -> 86.67 | Hurt |
| Add center point to H-Box-M (ablation) | SAM · HRSC2016 testing set | mIOU_I: 40.54 -> 24.54 | Hurt |
| Add H-Box-M and center point to H-Box (ablation) | SAM · HRSC2016 testing set | mIOU_I: 89.97 -> 59.71 | Hurt |
| Add center point to R-Box-M (ablation) | SAM · HRSC2016 testing set | mIOU_I: 65.54 -> 26.49 | Hurt |
Closest papers by meaning
- ROS-SAM: High-Quality Interactive Segmentation for Remote Sensing Moving Object (CVPR 2025 · similarity 0.91)
- Towards Open-Vocabulary Remote Sensing Image Semantic Segmentation (AAAI 2025 · similarity 0.88)
- InstructSAM: A Training-free Framework for Instruction-Oriented Remote Sensing Object Recognition (NeurIPS 2025 · similarity 0.87)
- ZoRI: Towards Discriminative Zero-Shot Remote Sensing Instance Segmentation (AAAI 2025 · similarity 0.87)
- Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing Community (AAAI 2025 · similarity 0.87)
- SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with Less than 0.2% Training Cost (CVPR 2025 · similarity 0.86)
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.