Selected work

Representative Papers

ELMZip: Onboard Satellite Image Compression via Extreme Learning Machines for Efficient Downlink

Aug 07, 2026

This study addresses the downlink bottleneck in small satellite multispectral imaging, where large data volumes and limited communication windows challenge conventional compression methods that struggle with the nonlinear statistical characteristics of multi-band, multi-resolution imagery. To overcome this, the paper proposes ELMZip, a novel on-board image compression framework that introduces extreme learning machines (ELMs) into spaceborne processing. By integrating domain decomposition and random feature mapping, ELMZip formulates image representation as a convex least-squares problem, enabling efficient neural implicit modeling without backpropagation. An asymmetric protocol transmits only compact output weights, drastically reducing downlink payload. The approach achieves high-fidelity reconstruction while substantially minimizing data return volume, thereby enabling real-time remote sensing analytics on resource-constrained platforms.

0 citationsRead paper

Summarize First, Download Later: Onboard VLMs for Bandwidth-Efficient Earth Observation

Aug 07, 2026

This study addresses the challenge of limited downlink bandwidth in Earth observation satellites, which often causes delays or loss of high-resolution remote sensing data, thereby compromising time-sensitive applications. To overcome this, the authors propose a semantic-driven downlink paradigm—“summarize first, download later”—wherein a lightweight vision-language model is deployed onboard to generate natural language summaries of acquired imagery. Ground users then interactively verify critical information via visual question answering (VQA) and selectively request full-resolution images only when necessary. This approach pioneers the integration of vision-language models and interactive VQA into space-to-ground communications, shifting from passive bulk transmission to semantic-aware, active dialogue. Experiments on an NVIDIA Jetson platform demonstrate that the proposed method substantially reduces bandwidth consumption while accelerating information retrieval for time-critical tasks.

0 citationsRead paper

Few-Shot Open-Vocabulary Remote Sensing Segmentation via Textual Inversion

Jul 28, 2026

This work addresses the significant performance drop of open-vocabulary remote sensing image segmentation on unseen categories, which stems from the misalignment between generic textual queries and the domain-specific visual-semantic space of remote sensing imagery. To bridge this gap, the study introduces textual inversion into this task for the first time, learning category-specific text embeddings from only a few examples to replace original class names. This enables purely text-driven few-shot inference under a frozen vision-language model, without modifying the model architecture or incorporating visual prompts. Evaluated on representative benchmarks, the proposed method boosts the mean Intersection-over-Union (IoU) for affected categories from 3.9 to 39.4 and consistently outperforms existing few-shot approaches that rely on visual prompting across eight remote sensing datasets.

0 citationsRead paper

FROST: Training-Free Few-Shot Segmentation with Frozen Features and Nonparametric Statistics

Jun 30, 2026

This work addresses the challenge of few-shot segmentation in remote sensing imagery, where scarce annotations and intra-class multimodality hinder performance. The authors propose a training-free segmentation method that leverages frozen DINOv3 self-supervised features to model foreground and background as point cloud distributions on the unit hypersphere. Departing from conventional single-prototype representations, the approach introduces a non-parametric density ratio for the first time and employs a Bayesian decision threshold for pixel-wise classification. All hyperparameters—including kernel bandwidth and spatial gating—are derived directly from the support set, enabling the decision boundary to automatically sharpen as more reference samples are provided. Evaluated across 17 remote sensing benchmarks, the method significantly outperforms existing techniques, achieving a 5.6% absolute gain in single-shot mIoU, with consistent performance improvements as the support set size increases, all while maintaining a lightweight model architecture.

0 citationsRead paper

FLAME: Physics-Guided Neural Operators for Onboard Satellite Methane Detection in Hyperspectral Imagery

May 31, 2026

This work addresses the challenges of high computational cost and insufficient accuracy in deep learning–based detection of methane emission sources from spaceborne hyperspectral imagery. To this end, we propose FLAME, a physics-guided lightweight neural operator that explicitly embeds physical priors of methane absorption into its architecture—a first in this domain. FLAME achieves significantly improved detection accuracy and markedly reduced false alarm rates with minimal model parameters, thereby satisfying the stringent real-time constraints of onboard satellite hardware. Experimental results demonstrate that FLAME attains state-of-the-art accuracy on standard methane detection benchmarks, reducing pixel-level false positives by nearly threefold compared to the strongest neural baseline while maintaining the lowest parameter count, thus effectively balancing precision and efficiency.

0 citationsRead paper

Recent publications

Latest Papers

ELMZip: Onboard Satellite Image Compression via Extreme Learning Machines for Efficient Downlink

Aug 07, 2026

This study addresses the downlink bottleneck in small satellite multispectral imaging, where large data volumes and limited communication windows challenge conventional compression methods that struggle with the nonlinear statistical characteristics of multi-band, multi-resolution imagery. To overcome this, the paper proposes ELMZip, a novel on-board image compression framework that introduces extreme learning machines (ELMs) into spaceborne processing. By integrating domain decomposition and random feature mapping, ELMZip formulates image representation as a convex least-squares problem, enabling efficient neural implicit modeling without backpropagation. An asymmetric protocol transmits only compact output weights, drastically reducing downlink payload. The approach achieves high-fidelity reconstruction while substantially minimizing data return volume, thereby enabling real-time remote sensing analytics on resource-constrained platforms.

0 citationsRead paper

Summarize First, Download Later: Onboard VLMs for Bandwidth-Efficient Earth Observation

Aug 07, 2026

This study addresses the challenge of limited downlink bandwidth in Earth observation satellites, which often causes delays or loss of high-resolution remote sensing data, thereby compromising time-sensitive applications. To overcome this, the authors propose a semantic-driven downlink paradigm—“summarize first, download later”—wherein a lightweight vision-language model is deployed onboard to generate natural language summaries of acquired imagery. Ground users then interactively verify critical information via visual question answering (VQA) and selectively request full-resolution images only when necessary. This approach pioneers the integration of vision-language models and interactive VQA into space-to-ground communications, shifting from passive bulk transmission to semantic-aware, active dialogue. Experiments on an NVIDIA Jetson platform demonstrate that the proposed method substantially reduces bandwidth consumption while accelerating information retrieval for time-critical tasks.

0 citationsRead paper

Few-Shot Open-Vocabulary Remote Sensing Segmentation via Textual Inversion

Jul 28, 2026

This work addresses the significant performance drop of open-vocabulary remote sensing image segmentation on unseen categories, which stems from the misalignment between generic textual queries and the domain-specific visual-semantic space of remote sensing imagery. To bridge this gap, the study introduces textual inversion into this task for the first time, learning category-specific text embeddings from only a few examples to replace original class names. This enables purely text-driven few-shot inference under a frozen vision-language model, without modifying the model architecture or incorporating visual prompts. Evaluated on representative benchmarks, the proposed method boosts the mean Intersection-over-Union (IoU) for affected categories from 3.9 to 39.4 and consistently outperforms existing few-shot approaches that rely on visual prompting across eight remote sensing datasets.

0 citationsRead paper

FROST: Training-Free Few-Shot Segmentation with Frozen Features and Nonparametric Statistics

Jun 30, 2026

This work addresses the challenge of few-shot segmentation in remote sensing imagery, where scarce annotations and intra-class multimodality hinder performance. The authors propose a training-free segmentation method that leverages frozen DINOv3 self-supervised features to model foreground and background as point cloud distributions on the unit hypersphere. Departing from conventional single-prototype representations, the approach introduces a non-parametric density ratio for the first time and employs a Bayesian decision threshold for pixel-wise classification. All hyperparameters—including kernel bandwidth and spatial gating—are derived directly from the support set, enabling the decision boundary to automatically sharpen as more reference samples are provided. Evaluated across 17 remote sensing benchmarks, the method significantly outperforms existing techniques, achieving a 5.6% absolute gain in single-shot mIoU, with consistent performance improvements as the support set size increases, all while maintaining a lightweight model architecture.

0 citationsRead paper

FLAME: Physics-Guided Neural Operators for Onboard Satellite Methane Detection in Hyperspectral Imagery

May 31, 2026

This work addresses the challenges of high computational cost and insufficient accuracy in deep learning–based detection of methane emission sources from spaceborne hyperspectral imagery. To this end, we propose FLAME, a physics-guided lightweight neural operator that explicitly embeds physical priors of methane absorption into its architecture—a first in this domain. FLAME achieves significantly improved detection accuracy and markedly reduced false alarm rates with minimal model parameters, thereby satisfying the stringent real-time constraints of onboard satellite hardware. Experimental results demonstrate that FLAME attains state-of-the-art accuracy on standard methane detection benchmarks, reducing pixel-level false positives by nearly threefold compared to the strongest neural baseline while maintaining the lowest parameter count, thus effectively balancing precision and efficiency.

0 citationsRead paper