Towards Text-Only Remote Sensing Scene Classification via Semantic Proxy
cs.CV
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/sstary/SSRS
Terminology
Sources
- Neural Plasticity-Inspired Multimodal Foundation Model for Earth Observation
- DINOv3
- AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data
- DGTRSD & DGTRS-CLIP: A Dual-Granularity Remote Sensing Image-Text Dataset and Vision Language Foundation Model for Alignment
- GeoRSMLLM: A Multimodal Large Language Model for Vision-Language Tasks in Geoscience and Remote Sensing
- LLaVA-OneVision: Easy Visual Task Transfer
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs