Research map / Detection and segmentation / Open-set and few-shot detection
From Visual Primitives to Semantic Masks: Fine-Grained Visual-Linguistic Alignment for Open-Vocabulary Remote Sensing Image Segmentation
Yuchen Deng, Yang Xu, Zhihui Wei, Zebin Wu
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 dynamic prototype injection (DPI) (ablation) | SAM 3 · FG-OVSSRS Bench: Cloud | mIoU (%): 29.56 -> 29.68 | Improved |
| add DPI (ablation) | SAM 3 · FG-OVSSRS Bench: YRCC | mIoU (%): 52.66 -> 55.25 | Improved |
| add DPI (ablation) | SAM 3 · FG-OVSSRS Bench: Rescue | mIoU (%): 35.76 -> 36.67 | Improved |
| add static prototype injection (SPI) to DPI (ablation) | SANO3 · FG-OVSSRS Bench: Cloud | mIoU (%): 29.68 -> 30.11 | Improved |
| add SPI to DPI (ablation) | SANO3 · FG-OVSSRS Bench: YRCC | mIoU (%): 55.25 -> 56.46 | Improved |
| add SPI to DPI (ablation) | SANO3 · FG-OVSSRS Bench: Rescue | mIoU (%): 36.67 -> 36.82 | Improved |
| add iterative information-gain visual prompting (IGVP) (ablation) | SANO3 · FG-OVSSRS Bench: Cloud | mIoU (%): 30.11 -> 30.70 | Improved |
| add IGVP (ablation) | SANO3 · FG-OVSSRS Bench: YRCC | mIoU (%): 56.46 -> 57.78 | Improved |
| add IGVP (ablation) | SANO3 · FG-OVSSRS Bench: Rescue | mIoU (%): 36.82 -> 36.84 | Improved |
| use VARA alignment instead of max cosine similarity matching (ablation) | SANO3 · FG-OVSSRS Bench: Cloud | mIoU (%): 30.30 -> 30.70 | Improved |
| use VARA instead of max cosine similarity (ablation) | SANO3 · FG-OVSSRS Bench: YRCC | mIoU (%): 57.11 -> 57.78 | Improved |
| use DINOv2 instead of MAE as VFM (ablation) | SANO3 · FG-OVSSRS Bench: YRCC | mIoU (%): 58.64 -> 57.78 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 5 of 5 on most shared results.
- SAM 3 — SAM 3: Segment Anything with Concepts (ICLR 2026) · better on 7 of 9 shared results
- SegEarth-OV — SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images (CVPR 2025) · better on 1 of 1 shared result
- CorrCLIP — CorrCLIP: Reconstructing Patch Correlations in CLIP for Open-Vocabulary Semantic Segmentation (ICCV 2025) · better on 1 of 1 shared result
- ClearCLIP — ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference (ECCV 2024) · better on 1 of 1 shared result
- ProxyCLIP — ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation (ECCV 2024) · better on 1 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
- Towards Open-Vocabulary Remote Sensing Image Semantic Segmentation (AAAI 2025 · similarity 0.92)
- SkySense-O: Towards Open-World Remote Sensing Interpretation with Vision-Centric Visual-Language Modeling (CVPR 2025 · similarity 0.90)
- SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing (AAAI 2024 · similarity 0.89)
- Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment (ICLR 2024 · similarity 0.89)
- Quality-Driven Curation of Remote Sensing Vision-Language Data via Learned Scoring Models (NeurIPS 2025 · similarity 0.88)
- VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding (NeurIPS 2024 · similarity 0.88)
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.
