Fine tuning CLIP with Remote Sensing (Satellite) images and captions

Unlocking the potential of vision language models on satellite imagery through fine-tuning

Ground-to-Satellite Knowledge Distillation for Crop Classification under Temporal and Geographic Shift

Ground-to-satellite knowledge distillation leverages ground-level field photographs to provide privileged supervision for crop classification models built on pretrained satellite embeddings. Using a frozen CLIP-based photo teacher, classifiers trained on AlphaEarth and TESSERA representations achieve consistent improvements over satellite-only baselines, especially under temporal and geographic shifts. The method enhances robustness without altering inference requirements, as photographs are used only during training.

RRS-10K: A Multitask Vision-Language Model Benchmark for Rare Remote Sensing Image Interpretation

arXiv:2607. 24810v1 Announce Type: new Abstract: Vision-language models (VLMs) have achieved strong performance on general remote sensing tasks.

RSGPNet: Geometric Prompting for Remote Sensing Open-Vocabulary Semantic Segmentation

arXiv:2606. 28410v1 Announce Type: cross Abstract: Open-vocabulary semantic segmentation (OVSS) enables text-guided segmentation of unseen objects, breaking fixed-class limitations to achieve open-world understanding.

Semi-Supervised Adaptation of Vision-Language Models for Image Classification

The paper introduces Self‑Evolutionary CLIP (SE‑CLIP), a semi‑supervised framework that adapts vision‑language models like CLIP to satellite imagery. SE‑CLIP uses a two‑phase pipeline: an initial warm‑up on a small set of annotated seeds followed by a recursive discovery phase that iteratively selects high‑confidence samples from unlabeled data. A class‑balanced selection strategy is applied to keep the evolving support set balanced, and experiments on the UCM and NWPU benchmarks show that SE‑CLIP outperforms existing semi‑supervised methods.

JL1-CC&QA: Extending the JL1-CD Benchmark with Change Captioning and Question Answering

arXiv:2606. 31745v1 Announce Type: cross Abstract: Remote sensing change detection (CD) traditionally focuses on pixel-level binary segmentation, which identifies where changes occur but neither what nor why.

AVID: A Weakly Aligned RGB-Infrared Dataset and Perturbation Benchmark for Tiny Aerial Targets

AVID is a new benchmark dataset for detecting tiny aerial targets, comprising 32,040 RGB‑infrared frame pairs from 115 videos with 35,952 bird and drone annotations at 320×256 resolution. The dataset focuses on very small objects, with 68.1% of targets having a geometric‑mean bounding‑box side of 8–16 pixels and 99.0% meeting the COCO small‑object criterion. It introduces metrics for cross‑modal alignment and an AVID‑C extension that simulates seven families of image degradation at five severity levels to study the impact of scale, degradation, and alignment on detection performance.

Structure-Aware Matching for Robust UAV Thermal-to-Satellite Geo-Localization

The paper introduces SAMF, a Structure-Aware Matching Framework designed to improve UAV thermal-to-satellite geo‑localization by exploiting stable cross‑modal structural cues. It comprises a Directional Structure Enhancement Module that captures directional and low‑frequency spatial patterns, and a Modality‑Aware Affine Remapping Module that aligns these enhanced features across modalities. Experiments on Boson‑nighttime and Thermal‑UAV‑Paired datasets demonstrate state‑of‑the‑art performance, with ablation studies confirming the complementary benefits of the two modules.

Fine-grained CLIP fine-tuning with self-annotated region alignment

Contrastive Language-Image Pre-training (CLIP) has been shown to have limitations in its fine-grained dense feature representation, due to its pre-training focusing on matching the whole image to a text description. Considering the large data and computational burden in pre-training a vision-language model from scratch, a series of works aim to enhance the fine-grained ability of CLIP through a fine-tuning scheme.

InfScene-SR: Seamless Super-Resolution of Arbitrarily Large Remote-Sensing Scenes via Variance-Preserving Joint Denoising

arXiv:2602.19736v3 Announce Type: replace Abstract: Diffusion models now give the best perceptual quality in super-resolution (SR), but their architecture and training confine them to small fixed cro...

FANVIDv2: Evaluating Video Super-Resolution by Face and Licence-Plate Recognition Under Compound Degradation

Video super-resolution (VSR) is normally judged by PSNR and SSIM on clips that were downsampled bicubically, although in surveillance its purpose is to make faces and licence plates \emph{recognisable...

A large-scale climate-aware satellite image dataset for domain adaptive land-cover semantic segmentation

The paper introduces CASID, a large-scale climate‑aware satellite image dataset for land‑cover semantic segmentation, comprising 980 5,000×5,000‑pixel images from 30 Asian regions across four climate zones (temperate monsoon, subtropical monsoon, tropical monsoon, and tropical rainforest). It is the first dataset to explicitly address domain gaps caused by climatic diversity, providing detailed analyses of image features, textures, category distributions, spectral values, and object shapes for each climate domain. Extensive experiments on CASID benchmark state‑of‑the‑art segmentation and unsupervised domain adaptation methods, establishing a robust baseline for future research.