Hugging Face Trending Papers
Data-Driven Vision-Language Models for Remote Sensing: A Survey
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Machine Learning
Oct 23
Data-Driven Vision-Language Models for Remote Sensing: A Survey
The paper surveys data-driven vision-language models (VLMs) for remote sensing (RS), highlighting a shift from model-centric to data-centric research. It reviews RS datasets designed for VLMs and offers a practical guide covering data construction, fine-tuning, and evaluation. The goal is to foster diverse, high-quality RS vision-language corpora that support broader AI development in the field.
arXiv Machine Learning
Jul 20
More with Less: a Large Scale Remote Sensing VLM with a Simple Recipe
arXiv:2607. 15942v1 Announce Type: cross Abstract: Remote sensing vision-language models are increasingly expected to support open-ended reasoning over Earth Observation data and a variety of tasks.
arXiv Computer Vision
Aug 25
SkyNative: A Native Multimodal Architecture for Remote Sensing Vision-Language Understanding
arXiv:2605.17949v2 Announce Type: replace Abstract: Remote sensing vision-language models (RS-VLMs) commonly employ a pretrained vision encoder and a projection module to map image features into the...
arXiv Computer Vision
Sep 25
GeoNLI - A Natural Language Interpreter for Satellite Imagery
GeoNLI introduces a unified, modular pipeline that combines advanced SAM variants with multimodal large language models to perform satellite image captioning, visual question answering (VQA), and visual grounding. The EarthMind model achieves strong results on captioning and VQA, while multiple RemoteSAM-SAM and DiffuSAM pipelines are used for grounding, ultimately employing a majority‑voting ensemble across several models. The system reports 82% captioning accuracy, 83.32% VQA accuracy, and 64.94% grounding accuracy, demonstrating improved consistency over task‑specific approaches.
arXiv Computer Vision
Sep 16
VPRef: A Cross-Domain Benchmark for Referring Remote Sensing Image Segmentation
The paper introduces VPRef, the first cross‑domain benchmark for Referring Remote Sensing Image Segmentation, containing 46,972 language‑image‑annotation triplets with a three‑tier linguistic hierarchy. It proposes a parameter‑efficient adaptation method based on the Segment Anything Model and Low‑Rank Adaptation, using pseudo‑label self‑training for visual drift and random multi‑granularity prompt mixing for textual drift. Experiments show the approach improves cross‑domain segmentation while altering only 1.08 % of the base model’s parameters, offering a strong baseline for future research.
Hugging Face Trending Papers
Sep 15
VPRef: A Cross-Domain Benchmark for Referring Remote Sensing Image Segmentation
Rapid advancements in vision-language models have propelled Referring Remote Sensing Image Segmentation (RRSIS) to the forefront of Earth observation. However, practical deployments suffer severe perf...