Research

Paper

AI LLM February 26, 2026

Spectrally Distilled Representations Aligned with Instruction-Augmented LLMs for Satellite Imagery

Authors

Minh Kha Do, Wei Xiang, Kang Han, Di Wu, Khoa Phan, Yi-Ping Phoebe Chen, Gaowen Liu, Ramana Rao Kompella

Abstract

Vision-language foundation models (VLFMs) promise zero-shot and retrieval understanding for Earth observation. While operational satellite systems often lack full multi-spectral coverage, making RGB-only inference highly desirable for scalable deployment, the adoption of VLFMs for satellite imagery remains hindered by two factors: (1) multi-spectral inputs are informative but difficult to exploit consistently due to band redundancy and misalignment; and (2) CLIP-style text encoders limit semantic expressiveness and weaken fine-grained alignment. We present SATtxt, a spectrum-aware VLFM that operates with RGB inputs only at inference while retaining spectral cues learned during training. Our framework comprises two stages. First, Spectral Representation Distillation transfers spectral priors from a frozen multi-spectral teacher to an RGB student via a lightweight projector. Second, Spectrally Grounded Alignment with Instruction-Augmented LLMs bridges the distilled visual space and an expressive LLM embedding space. Across EuroSAT, BigEarthNet, and ForestNet, SATtxt improves zero-shot classification on average by 4.2%, retrieval by 5.9%, and linear probing by 2.7% over baselines, showing an efficient path toward spectrum-aware vision-language learning for Earth observation. Project page: https://ikhado.github.io/sattxt/

Metadata

arXiv ID: 2602.22613
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-02-26
Fetched: 2026-02-28 05:45

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.22613v1</id>\n    <title>Spectrally Distilled Representations Aligned with Instruction-Augmented LLMs for Satellite Imagery</title>\n    <updated>2026-02-26T04:34:47Z</updated>\n    <link href='https://arxiv.org/abs/2602.22613v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.22613v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Vision-language foundation models (VLFMs) promise zero-shot and retrieval understanding for Earth observation. While operational satellite systems often lack full multi-spectral coverage, making RGB-only inference highly desirable for scalable deployment, the adoption of VLFMs for satellite imagery remains hindered by two factors: (1) multi-spectral inputs are informative but difficult to exploit consistently due to band redundancy and misalignment; and (2) CLIP-style text encoders limit semantic expressiveness and weaken fine-grained alignment. We present SATtxt, a spectrum-aware VLFM that operates with RGB inputs only at inference while retaining spectral cues learned during training. Our framework comprises two stages. First, Spectral Representation Distillation transfers spectral priors from a frozen multi-spectral teacher to an RGB student via a lightweight projector. Second, Spectrally Grounded Alignment with Instruction-Augmented LLMs bridges the distilled visual space and an expressive LLM embedding space. Across EuroSAT, BigEarthNet, and ForestNet, SATtxt improves zero-shot classification on average by 4.2%, retrieval by 5.9%, and linear probing by 2.7% over baselines, showing an efficient path toward spectrum-aware vision-language learning for Earth observation. Project page: https://ikhado.github.io/sattxt/</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-02-26T04:34:47Z</published>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Minh Kha Do</name>\n    </author>\n    <author>\n      <name>Wei Xiang</name>\n    </author>\n    <author>\n      <name>Kang Han</name>\n    </author>\n    <author>\n      <name>Di Wu</name>\n    </author>\n    <author>\n      <name>Khoa Phan</name>\n    </author>\n    <author>\n      <name>Yi-Ping Phoebe Chen</name>\n    </author>\n    <author>\n      <name>Gaowen Liu</name>\n    </author>\n    <author>\n      <name>Ramana Rao Kompella</name>\n    </author>\n  </entry>"
}