Topic
remote sensing
SARLO-80: New Dataset Combines Very-High-Resolution SAR and Optical Imagery with Language Descriptions
Researchers have released SARLO-80, a large-scale dataset combining very-high-resolution synthetic aperture radar (SAR) imagery, aligned optical imagery, and natural-language descriptions. Built from Umbra spotlight acquisitions, the dataset contains 119,566 triplets across 72 countries, standardized to 80cm slant-range resolution. It aims to advance multimodal foundation models for SAR by providing complex-valued measurements and native acquisition geometry.
TerraMind: First Any-to-Any Generative Multimodal Foundation Model for Earth Observation
Researchers have introduced TerraMind, the first any-to-any generative, multimodal foundation model for Earth observation (EO). Pretrained on dual-scale representations across nine geospatial modalities, it achieves beyond state-of-the-art performance on the PANGAEA benchmark and introduces a novel 'Thinking-in-Modalities' capability.
New Benchmark Reveals Remote Sensing AI Models Fail at Negation Comprehension
A new study introduces RS-Neg, the first benchmark to evaluate negation comprehension in remote sensing multimodal large language models. The evaluation reveals that advanced models exhibit hallucinations and performance degradation when handling negation. The proposed NeFo method, using about 5% unlabeled test samples, significantly improves negation understanding, with implications for critical applications like emergency response and logistics.
SLUM-i: AI Semi-Supervised Learning Maps Informal Settlements with Benchmark Dataset
A new AI framework called SLUM-i uses semi-supervised learning to map informal settlements in cities like Lahore, Karachi, and Mumbai. It introduces a benchmark dataset and achieves up to +5.9 pp mIoU improvement over existing methods.
FusionRS Dataset Advances Dual-Modal Vision-Language AI for Remote Sensing
Researchers introduced FusionRS, the first large-scale RGB-infrared-text dataset for dual-modal vision-language learning in remote sensing. The dataset pairs RGB and infrared images with scene and IR-aware captions, enabling models to achieve better alignment and retrieval than RGB-only approaches.
Multi-Modal Attention Model Achieves 94.9% Accuracy in Automated Disaster Damage Classification Using Satellite Imagery
Researchers have developed a novel deep learning framework that automates building damage classification from satellite imagery. The model uses a multi-modal attention mechanism to fuse pre- and post-disaster images, categorizing damage into four levels with 94.90% accuracy, significantly improving assessment speed and aiding emergency responders.
Improved Knowledge Distillation Framework Achieves 99.04% Accuracy for Land-Use Classification
A research paper on arXiv presents an improved knowledge distillation framework for compressing deep neural networks used in land-use image classification. By integrating hard label supervision with soft losses (KL divergence and cosine similarity), the method achieves 99.04% accuracy on three land-use datasets, outperforming baseline and single-loss distillation approaches while substantially reducing model size.
RSRCC Benchmark Uses Retrieval-Augmented Best-of-N Ranking for Remote Sensing Change Comprehension
RSRCC is a new benchmark for remote sensing change question-answering, containing 126k questions focused on localized, semantic changes. It uses a hierarchical semi-supervised curation pipeline with retrieval-augmented Best-of-N ranking to filter noisy candidates. The dataset is available online.
GeoRoPE: Ground-Aware Rotary Adaptation Enhances Remote Sensing Foundation Models
A new research paper introduces GeoRoPE, a ground-aware rotary adaptation method for remote sensing foundation models. It addresses scale mismatch by recalibrating token-level positional interactions, improving cross-resolution robustness and scale-sensitive representation learning. The method is parameter-efficient and compatible with existing models.