RefSegRS is a dataset for referring remote sensing image segmentation tasks, likely containing satellite imagery paired with descriptive text. It was created by JessicaYuan and associated researchers for the RRSIS project, as documented in a 2023 arXiv preprint. The dataset was last updated on HuggingFace in February 2024.
Use Cases
- Training models for referring expression comprehension in remote sensing imagery based on text-image pairs.
- Benchmarking segmentation algorithms that integrate visual and textual cues.
- Developing multimodal AI systems for automated analysis of satellite scenes described in text.
Strengths
- Dataset is associated with a published research paper (arXiv:2306.08625, 2023).
- Last update date is known (2024-02-01 09:47:36).
Limitations
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count is unknown, which may limit suitability assessment.
- Description metadata is limited; actual data quality requires manual inspection after download.
Provenance
- Source
- JessicaYuan
- Freshness
- Last updated 2024-02-01 09:47:36; freshness should be verified.