AlignJEPA: Predictive Vision-Language Alignment for Remote Sensing Foundation Models

• URL: http://arxiv.org/abs/2608.15456v1
• Date: Sun, 16 Aug 2026 00:27:07 GMT
• Title: AlignJEPA: Predictive Vision-Language Alignment for Remote Sensing Foundation Models
• Abstract summary: AlignJEPA is a JEPA-inspired predictive vision-language alignment framework for remote sensing foundation models.<n>We train and evaluate AlignJEPA on BigEarthNet.txt for natural-language Sentinel retrieval, evaluate cross-dataset adaptation on RSICD, and use RSVQA only as a closed-set representation probe.
• Score: 17.02495765712523
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Remote sensing (RS) foundation models provide transferable Earth observation representations across sensors, resolutions, and geographies, yet most remain weakly aligned with natural language, limiting natural-language archive search, image-text retrieval, and question-conditioned analysis. We propose AlignJEPA, a JEPA-inspired predictive vision-language alignment framework for remote sensing foundation models. AlignJEPA uses a pretrained AnySat visual encoder and a RemoteCLIP text encoder while training only a lightweight predictive alignment network. Instead of relying on global image--text contrastive alignment alone, the framework predicts remote-sensing text embeddings from masked visual foundation-model tokens. Its mask-aware multi-scale predictive aligner aggregates visible tokens at fine, regional, and global scales, jointly models them with a cross-scale Transformer, and projects the resulting representation into the text space using learned query pooling. Training combines semantic prediction with bidirectional contrastive retrieval. We train and evaluate AlignJEPA on BigEarthNet.txt for natural-language Sentinel retrieval, evaluate cross-dataset adaptation on RSICD, and use RSVQA only as a closed-set representation probe. AlignJEPA provides a parameter-efficient route for aligning Earth observation foundation models with language.

Related papers

• One Patch Is Enough: Reinforcement-Optimized Visual Token Grounding for MLLM-Based Scene Text Spotting [51.09550363815034]
  Scene text spotting requires high-precision alignment between textual recognition and spatial localization.<n>We propose Single-Patch Text Spotting (SPaTS), a vision-centric framework that routes each text instance through a single anchor visual token.<n>We show that SPaTS consistently and significantly outperforms both frontier closed-source MLLMs and OCR MLLMs.
  arXiv  Detail & Related papers  (2026-07-30T09:17:48Z)
• ExACT: Exemplar-Driven Calibrated Refinement for Training-Free Visual Grounding in Remote Sensing Images [51.53960096934913]
  Remote sensing visual grounding (RSVG) aims to locate specific objects in high-resolution RS imagery using free-form natural language descriptions.<n>Recent advances in multimodal large language models (MLLMs) show great potential for such open-vocabulary RSVG.<n>We propose Exemplar-driven Calibrated Refinement (ExACT), a training-free framework driven by a one-shot visual prompting mechanism.
  arXiv  Detail & Related papers  (2026-06-27T13:50:39Z)
• FLORO: A Multimodal Geospatial Foundation Model for Ecological Remote Sensing Across Sensors and Scales [65.4821703903285]
  FLORO is a multimodal foundation model designed to learn transferable representations from a small but highly diverse remote sensing corpus.<n> FLORO is pretrained using masked autoencoding on a heterogeneous combination of Sentinel-1, Sentinel-2, SkySAT imagery, elevation, and UAV-derived data.<n>We evaluated FLORO on the PANGAEA benchmark under a frozen-encoder protocol across scene classification, segmentation, and regression tasks.
  arXiv  Detail & Related papers  (2026-05-27T08:55:54Z)
• ProVG: Progressive Visual Grounding via Language Decoupling for Remote Sensing Imagery [20.725910735285762]
  Remote sensing visual grounding aims to localize objects in remote sensing imagery according to natural language expressions.<n>We propose textbfProVG, a novel RSVG framework that improves localization accuracy by decoupling language expressions into global context, spatial relations, and object attributes.<n>ProVG consistently outperforms existing methods, achieving new state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-04-02T10:59:19Z)
• Unifying Heterogeneous Multi-Modal Remote Sensing Detection Via Language-Pivoted Pretraining [59.2578488860426]
  Heterogeneous multi-modal remote sensing object detection aims to accurately detect objects from diverse sensors.<n>Existing approaches largely adopt a late alignment paradigm, in which modality alignment and task-specific optimization are entangled during downstream fine-tuning.<n>We propose BabelRS, a unified language-pivoted pretraining framework that explicitly decouples modality alignment from downstream task learning.
  arXiv  Detail & Related papers  (2026-03-02T11:38:12Z)
• Semantically Aware UAV Landing Site Assessment from Remote Sensing Imagery via Multimodal Large Language Models [5.987458168544856]
  Safe UAV emergency landing requires understanding complex semantic risks invisible to traditional geometric sensors.<n>We propose a novel framework leveraging Remote Sensing (RS) imagery and Multimodal Large Language Models (MLLMs) for context-aware landing site assessment.
  arXiv  Detail & Related papers  (2026-02-01T11:30:03Z)
• Loc$^2$: Interpretable Cross-View Localization via Depth-Lifted Local Feature Matching [80.57282092735991]
  We propose an accurate and interpretable fine-grained cross-view localization method.<n>It estimates the 3 Degrees of Freedom (DoF) pose of a ground-level image by matching its local features with a reference aerial image.<n> Experiments show state-of-the-art accuracy in challenging scenarios such as cross-area testing and unknown orientation.
  arXiv  Detail & Related papers  (2025-09-11T18:52:16Z)
• Language Driven Occupancy Prediction [13.35971455725581]
  We introduce LOcc, an effective and generalizable framework for open-vocabulary occupancy prediction.<n>Our pipeline presents a feasible way to dig into the valuable semantic information of images, transferring text labels from images to LiDAR point clouds and ultimately to voxels.<n>By replacing the original prediction head of supervised occupancy models with a geometry head for binary occupancy states and a language head for language features, LOcc effectively uses the generated language ground truth to guide the learning of 3D language volume.
  arXiv  Detail & Related papers  (2024-11-25T03:47:10Z)
• Enhancing JEPAs with Spatial Conditioning: Robust and Efficient Representation Learning [7.083341587100975]
  Image-based Joint-Embedding Predictive Architecture (IJEPA) offers an attractive alternative to Masked Autoencoder (MAE) IJEPA drives representations to capture useful semantic information by predicting in latent rather than input space. Our "conditional" encoders show performance gains on several image classification benchmark datasets.
  arXiv  Detail & Related papers  (2024-10-14T17:46:24Z)
• YORO -- Lightweight End to End Visual Grounding [58.17659561501071]
  YORO is a multi-modal transformer encoder-only architecture for the Visual Grounding (VG) task. It consumes natural language queries, image patches, and learnable detection tokens and predicts coordinates of the referred object. YORO is shown to support real-time inference and outperform all approaches in this class (single-stage methods) by large margins.
  arXiv  Detail & Related papers  (2022-11-15T05:34:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.